SEO Dünyasının En Büyük Haberi: 1922 Farklı SEO Sıralama Faktörü Sızdırıldı.

asciyamagi · 28 Ocak 2023

Bir Yandex çalışanı tarafından, 1922 arama sıralaması faktörünün de yer aldığı birçok Yandex ürününe ait kaynak kodlar popüler bir hacker platformunda servis edildi.

yandex seo kritlerleri 1922 maddelik sızıntı

44.7 GB büyüklüğündeki sızıntıda;

Yandex search engine and indexing bot
Yandex Maps
Alice (AI assistant)
Yandex Taxi
Yandex Direct (ads service)
Yandex Mail
Yandex Disk (cloud storage service)
Yandex Market
Yandex Travel (travel booking platform)
Yandex360 (workspaces service)
Yandex Cloud
Yandex Pay (payment processing service)
Yandex Metrika (internet analytics) ‘e ait verilerin bulundupu görünüyor.

Sızıntı, en azından Temmuz 2022 itibarıyla Yandex’in arama algoritmasında kullandığı 1.922 sıralama faktörünü ortaya çıkardı.

Yandex source code hacked! Complete list of 1900+ ranking factors can be downloaded here: https://t.co/8yiP0Yo0yk

— Martin MacDonald (@searchmartin) January 27, 2023

Martin MacDonald bunu bugün Twitter’da; “Yandex hack’i muhtemelen SEO’da yıllardır meydana gelen en ilginç şey.” olarak ifade etti.

The Yandex hack is probably the most interesting thing to have happened in SEO in years.

— Martin MacDonald (@searchmartin) January 27, 2023

Yandex bunu Saldırı değil “sızıntı” olarak tanımlıyor.

Gridory Bakunov’un bir haber sitesine yaptığı açıklamada Yandex, sistemlerinin saldırıya uğramadığını ve eski bir çalışanın kaynak kodu deposunu sızdırdığını söyledi.

Kod, popüler bir bilgisayar korsanlığı forumunda göründüğü için ilk başta Yandex’in saldırıya uğradığı düşünüldü. Yandex bunu yalanladı ve şu açıklamayı yaptı:

“Yandex hacklenmedi. Güvenlik servisimiz, kamuya açık bir dahili depodan kod parçaları buldu, ancak içerik, Yandex hizmetlerinde kullanılan deponun mevcut sürümünden farklı.

Depo, kodu depolamak ve kodla çalışmak için bir araçtır. Kod, çoğu şirket tarafından dahili olarak bu şekilde kullanılır.

Depolar, kodla çalışmak için gereklidir ve kişisel kullanıcı verilerinin depolanması için tasarlanmamıştır. Kaynak kodu parçalarının halka açıklanmasının nedenleriyle ilgili bir iç soruşturma yürütüyoruz, ancak kullanıcı verilerine veya platform performansına yönelik herhangi bir tehdit görmüyoruz.”

Sızıntıyla ilgili daha fazla bilgiyi Techmeme’de bulabilirsiniz.

Yandex SEO Sızıntısı SEO Algoritma 1922 listesi indir

Yandex SEO Algoritması listesi. MacDonald, SEO 1.922 faktörün tam listesini burada paylaştı. Linkten factors_gen indirebilirsiniz.

Yandex SEO Sızıntısı erken analizi.

Alex Buraks, çeşitli sıralama faktörlerini analiz ederek iki Twitter dizisi oluşturdu – 1. Thread , 2. Thread -. Michael King’den ilginç bir Twitter dizisi daha var.

The Yandex hack is probably the most interesting thing to have happened in SEO in years.

— Martin MacDonald

(@searchmartin) January 27, 2023

Leaked Yandex ranking factors analysis part 2, let's go.

[

THREAD]
— Alex Buraks (@alex_buraks) January 28, 2023

Aight y'all.

Let's get started with this Yandex thing.

First thing, I want to give props and a shout out to @benwills who was the first to tell me about the leak and did a lot of initial leg work to make sense of where things live. He's the real MVP.

— Mic King (@iPullRank) January 27, 2023

Dan Taylor ayrıca Yandex Veri Sızıntısı: Rus Arama Haberlerinde Arama Algoritmaları Hakkında Öğrendiklerimiz adlı makalesinde bazı bulguları paylaşıyor.

Yandex SEO Kriterleri Nelerdir?

Yandex’in sıralama faktörlerinin çoğu, görmeyi beklediğiniz şeylerdir –

PageRank,
metin alaka düzeyi,
içerik yaşı ve tazeliği,
çok sayıda son kullanıcı davranış faktörü,
ana bilgisayar güvenilirliği ve bağlantıyla ilgili birçok faktör (ör. yaş, alaka düzeyi, vb.)
SEO uzmanlarının şaşırtıcı bulduğu sıralama faktörlerinden bazıları:
tekil ziyaretçi sayısı,
organik trafiğin yüzdesi,
sorgular arasında ortalama etki alanı sıralaması.

Ve Taylor’ın belirttiği gibi, sıralama faktörlerinden 244’ü kullanılmamış ve 988’i kullanımdan kaldırılmış olarak kategorize edildi, “bu, belgenin %64’ünün ya aktif olarak kullanılmadığı ya da yerinin değiştirildiği anlamına geliyor – yani daha çok ~690 potansiyel sıralama faktörü ve bir çoğu ince betimlemeler içeriyor.”

Yandex SEO Kriter Arama Aracı ile inceleyin.

Yandex SEO 1922 arama faktörü sızdırıldı

SEO Sıralama Faktörü Gezgini. Rob Ousbey, çeşitli sıralama faktörlerini aramak için bir araç olan Yandex SEO Sıralama Faktörü Gezgini’ni yarattı. Linke tıklayarak ilerletebilirsiniz.

Yandex SEO Kriterleri nelerdir?

Index	Name
0	PR Page Rank. The factor will be remarked.
1	TR
2	LR Link relevance. The factor will be remarked.
3	PrBonus Priority bonus, priority 7 – text priority. The binary factor, matters 0 for all monosyllabic requests, and the value of 1 for almost all two or more words, except for a very small number of answers for which there is not a single link that has passed quorum, and the text also did not pass the quorum.
4	TRp1 Stript priority for TR is a text priority – there are all the words of the request somewhere in the document (while they pass contextual restrictions on the request, for example, both words DB in one sentence).
5	TRp2 PHRASE priority for TR is a text priority – there are all the words of the request in a row in the document.
6	LRp1 (strict) there is all the words of the request in one link.
7	LRp2 (Phrase) There are all the words of the request in a row in one line.
8	TRtitle The presence of an accurate phrase (request text) in the header (more precisely, in the first sentence of the document). Contextual restrictions and feet are taken into account exactly as in TRP2, i.e. Factor [8] Minors Factor [5]
9	TRhr There was a plot that passed the quorum in which all the word positions are designated as those who have the relevance of Best_relev (title or Meta Keywords).
10	Removed_10
11	News This is the news (determined by the characteristic ((http://wiki.yandex-team.ru/jandeksp...iekomponenty/klassificacionnye?v=tkd#h45859-3 Patterns in URL $))))).
12	Shop This is a proposal store (determined by the characteristic ((http://wiki.yandex-team.ru/jandeksp...iekomponenty/klassificacionnye?v=tkd#h45859-4 Patterns in Url ‘))))))))). Not used (depreded)
13	Cat This is a catalog (determined by the characteristic ((http://wiki.yandex-team.ru/jandeksp...ormula/tekushhiekomponenty/klassificacionnye? .
14	YaBar Attendance from the bar – ((http://wiki.yandex-team.ru/andrejjkostjagin/yabarlog/hoststat data description)). The factor will be remarked.
15	Long Long document (the longer the document, the greater the value of the factor).
16	TRhitw Hitweigt is a variant of textual relevance, in which the weights of all hits are considered equal (i.e., they do not take into account the allowances for title and the proximity of words). In this case, the corresponding hits must be restricted by the syntactic sorcerer, i.e. We can assume that the TRHITW factor is 0 and only when Softandok is 0
17	LongQuery The amount of IDF words of the request. The name does not reflect the essence: for example, for the request of ‘Gadyach’ this factor will be more than for the request of ‘Moscow Peter Yekaterinburg Samara’.
18	PureText Long text without links.
19	Root This is a muzzle.
20	Removed20
21	Removed21
22	Geo Means the coincidence of the region of the user and the site at the level of countries. Binar factor: 1-rush, 0-no. It is based on ((http://wiki.yandex-team.ru/ Yandexposisk/ Classification of Sytraitniki/ Geographic/Sospolzanievpoysk Geoklassification of sites)))))))
23	SubqueryThMatch Coincidence of thematic spectra of request and document. Request themes-the result of work ((http://wiki.yandex-team.ru/evgenijjkroxalev/subquery Rules of the sorcerer Subquerysearch)) The subject of the document is taken from Yandex-Catalog
24	SR The complex Static Rank is assembled from static components according to a separate formula ((http://wiki.yandex-team.ru/jandekspoisk/kachestvopoiska/obshayAfermula/tekushhiekomponenty/#oftnd1 *))).
25	TRref The factor about the number of Refines. In the queries, there is a feature of user refines (” word that is faced with a percentage sign ‘). According to the idea, this means something like ‘it would be good if the word in the document was’. The only famous ((http://staff.yandex-team.ru/gulin Andrey Gulin)) the valuable use of this feature is a request [ %official %site name of the film]. This feature is unknown to users, because Not described in any documentation. It is planned that it will disappear from the tongue of requests, but in the sorcerer the words with the priority of User_refine will remain. The factor indicates how much the maximum user_refine was simultaneously found in the framework of a single hit in the quorum. It is believed that there are from 0 to 3 (if> 3, then it is believed that 3). This number is waved in the half interval [0.1]
26	TRboost The number for which some linseed factors are multiplied (namely, factors number 6, 7, 47, 66), if text relevant 0, and there are few links
27	TRLRlemma In textual relevance, Lemma coincides.
28	TrafgraphOutAll_share_d Remapped mascot feature TrafgraphOutAll_share_d
29	RelevSentsDssm DSSM model, trained for reformulations, in the document uses relevant to the request of the proposal
30	FreshNewsDetectorPredict The value of the news detector calculated in the Hippo. Always 0 with a detector value less than the threshold.
31	LRHitNum100 The transformed number of words of the request in all url linos.
32	LRHitNumGt16 The document LR> 20 The number of words of the words of the request in the Links> 16, the factor about LR.
33	PctLinks For documents with a high LR, a normalized lincat relevance excluding proximity, for documents with a low LR 0
34	HasLR URL High LR.
35	LinkQuality The quality of incoming links (the classifier of the bream) is broken, cm [405]
36	AliceMusicTrackTitleCosineMatchMaxPrediction The value of the cosinematchmaxprediction factor for the Stryim ALICEMUSIC
37	NumLinks The number of incoming links. Remembrance.
38	PopularQ The popularity of the request
39	TRUnmapped TR divided by a cube of the number of words in a request and transformed by a standard REMAPTR.
40	RusLang The language of the document is Russian.
41	AddTime The time of adding a page, more – a more old document; The root is placed from time displayed at the interval [0.1] so that 3+ years gives 1.
42	IsMainPage If the main page of the owner (most often a second -level domain, for example xxxx.ru), then the factor is 1. For bums, hosting, personal blogs, etc. (for example, Lifejornal, People.ru, etc.) – domains of the third level (such as xxxxx.narod.ru) will also have an equal factor 1.
43	AddTimeMP The time for adding the main page of the owner (host?) Will be remaped like Addtime.
44	AliceMusicTrackTitleAnnotationMaxValueWeighted The value of the factor annotationmaxvalueEWEEGTED for Stryim ALICEMUSIC
45	QueryURLClicksPCTR How often they click in this URL for this request – CTR blasting for the correction factor
46	TextBM25 Simple BM25 in text.
47	LinkBM25 Simple BM25 for links, the weights of the braces are not taken into account.
48	TLBM25 Simple BM25 in text and links at the same time.
49	TLp1 All the words of the request are in the text + links.
50	Adv There is advertising on the site.
51	YandexAdv On the site there is an advertisement for Yandex.
52	NoSpam The Classifier of Spam for Picks from Antispam recognized the site not (!) Spam. Those. 0 = spam, 1 = good.
53	TxtPair Simple BM25 in pairs of words – we take all pairs of words of the request and consider the number of their entry into the text of the document. In the quality of the weight of the pair we use the sum of the scales of words. It does not work if there is a stop-word in the request
54	LnkPair The same as txtpair, but for links; Link weights are not taken into account.
55	TxtBreak BM25 from the number of sentences in the document in which it occurs.
56	TxtHead BM25 according to only in the heading.
57	TxtHiRel BM25 according to only with High Rel-bots (‘significant’, with the allocation (<b> ITP)).
58	Removed_58
59	WordCount Min (number of words of request/10, 1.f)
60	InvWordCount 1 / quantity_lov_v_
61	HasNoTR The document has no TR.
62	HasNoLR The document has no LR.
63	HasNoQueryURLShows For this Urla, for this request, there is no information about clickness 1 – request or request -URLA in the click database, 0 – query URL in the clicks database
64	HasNoQueryShows For this request, there is no information about clickability 1 – there is no request in the click database, 0 – the request is in the click database.
65	Hops The number of hops of Url inpans (such as less – closer to the muzzle, the lower the value (0 – the muzzle, 1 – from the muzzle cannot be reached, 0 <can get from the muzzle <1). Normal value for the root of the nosta 0.0039).
66	LogLR Logarithm from LR, linearly displayed in [0.1].
67	TxtPairEx the presence of pairs of words in the exact form
68	TxtBreakEx the number of sentences in which there are many words in the exact form
69	TxtHeadEx the presence of words in the header in the exact form
70	TxtHiRelEx BM25 in the exact form
71	TxtBm25Ex Simple BM25 in the exact form.
72	TxtPairSy the presence of pairs of words taking into account synonyms (> = txtpair)
73	TxtBreakSy the number of sentences in which there are many words taking into account synonyms
74	TxtHeadSy the presence of words in the header, taking into account synonyms
75	TxtHiRelSy BM25 taking into account synonyms
76	TxtBm25Sy Simple BM25 taking into account synonyms.
77	QueryDOwnerClicksPCTR How often they click in the URLs of this Domainid for this request – Ctr Domainid blasting for the correction factor
78	HasNoQueryDOwnerShows For this Domainid for this request, there is no information about clickability 1 – request or request -owner is not in the clicks database, 0 – the request for clicks is in the database of clicks
79	OwnerClicksPCTR The owner’s clickness regardless of the request
80	Megafon The relative frequency of the words in the links (1 – the words of the request are often found in links, 0.3 – rarely); More precisely, the value of this factor is pessimized provided: TR = 0 && LR = 0 & (there is not a single link with all the words of the request) && (did not pass the quorum) && (at least one pair of words of the request is found in the text)
81	XLRp0 There are all the words of the request in the links
82	XLRp1 There are all the words of the request in one link
83	XLRp2 There is a link that has passed quorum
84	XLRgood What is the share of “good” links
85	XLRmanyBad How many “bad” links (bad = DPR = 0)
86	XLRmaxDpr Maximum DPR links
87	XLRtfidf TFIDF ordinary TF*IDF by links. The frequency of the word in the links is multiplied by the reverse document frequency and summarized in all words, then it is normalized to the length of the document.
88	XLRrelev Linkovaya relevance by Gulina
89	XLRrelev200 Linkovaya relevance by Gulina
90	XLRlogRelev Linkovaya relevance by Gulina
91	BFexact There is an exact form of all words of the request in the text/lincers
92	BFlemma There is a lemma of all the words of the request in the text/lincers
93	SoftAndOk The document passed Softand on the restrictions of the syntactic sorcerer. Only for documents with textual relevance. For monosyllabic requests, always 1.
94	NewLinkQuality The quality classifier of incoming links 2 is broken, cm [407]
95	Ukrainian It is equal to one if the site has a Ukrainian geoist (i.e. 1 – Ukrainian site)
96	IsBlog Page from the blogochosting
97	IsLivejournal Page with Livejournal.com
98	Removed_98
99	Spam2 Automatic classifier spam named after Alekseeva, the likelihood that the website spam (0 is not spam, 1- spam)
100	TextFeatures The quality of the text. It is considered a rather complex formula
101	TextLike Text quality (classifier Alekseeva)
102	Removed_102
103	Removed_103
104	YaBarCoreOwner The core of the audience of owners according to Yandex.Mrazusing
105	YaBarCoreHost The core of the audience of the hosts according to Yandex.Mrazusing
106	HasYaBarCore Does the host have a host
107	SpamKarma Spam karma named after antispamers is the likelihood that the host is spam; based on Whois information
108	MusicQ The musicality of the request. The results of the sorcerer Anton Konygin.
109	XLExactMatches The number of links that exactly coincide with a request
110	DocLen Document length in sentences
111	UrlLen The length of the URL, divided by 5
112	QueryNonCommerciality The commercial request for the dictionary of phrases from Direct: 0 – maximum commercial, 1 – minimal.
113	HostSize The size of the Host named after Raskovalov in the documents without taking into account the takes (each double is taken into account in the factor by an independent document)
114	IsHTML Document type – HTML
115	LinkSpeed The number of reverse dispersion times of the appearance of links with the words of the request
116	XThLRrelev Link relevance, taking into account thematicity
117	XThLRrelev200 Link relevance, taking into account thematicity
118	XThLRlogRelev Link relevance, taking into account thematicity
119	XLerfLRrelev Link relevance, taking into account the quality of each link
120	XLerfLRrelev200 Link relevance, taking into account the quality of each link
121	XLerfLRlogRelev Link relevance, taking into account the quality of each link
122	XLerfThLRlogRelev Link relevance, taking into account the quality of each link and thematicity of each link
123	XNonCommLRlogRelev Link relevance, taking into account the non -profitability of each link
124	XNonCommThLRlogRelev Link relevance, taking into account the non -profitability of each link and thematic
125	XNonCommLerfLRlogRelev Link relevance, taking into account the non -profitability of each link and quality of each link
126	XNonCommLerfThLRlogRelev Link relevance, taking into account the non -profitability of each link, the quality of each link and thematicity
127	GeoCityProxim Means the coincidence of the region mentioned in the request and found sites at the level of areas. Binar factor: 1-rush, 0-no. It is based on ((http://wiki.yandex-team.ru/ Yandexposisk/ Classification of Sytraitniki/ Geographic/Sospolzanievpoysk Geoklassification of sites)))))))
128	LinksWithWordsPercent The percentage of incoming links with the words of the request
129	LinksWithAllWordsPercent The percentage of incoming links with all the words of the request
130	PornoQuery Are there any words from Yweb/Pornofilter/Porno.query.
131	IsPorno Document from porn kitski
132	IsComm A document from a commercial clay. Not used (depreded)
133	IsFake Fast document
134	IsSEO The page title contains commercial vocabulary. Not used (depreded)
135	IsWiki page from ru.wikipedia.org
136	IsEShop Commercial page (Classifier Savina)
137	GeoRegionProxim
138	HasNoAllWordsTRSy The document does not have all the words of the request (with an accuracy to a synonym)
139	NumWordsTRSy The percentage of the words of the request in the document (with an accuracy to a synonym)
140	HasAllWordsTRSy The document has all the words of the request (with an accuracy to a synonym)
141	NumWordsLR The percentage of the words of the request in the links (with an accuracy to a synonym)
142	HasAllWordsLR There are all the words of the request in the links (with an accuracy to a synonym)
143	PayDetectorPredict The value of the commerce detector calculated in the Hippo.
144	TxtInvPair Tr by pairs of words in the reverse order
145	LnkInvPair Lr by pairs of words of the request in the reverse order
146	TxtSkipPair TR by pairs of words of the request through one word in texts
147	LnkSkipPair Lr by pairs of words of the request through one word in texts
148	NumWordsTRFm The percentage of all the words of the request in the text (with an accuracy to the form)
149	HasAllWordsTRFm The document has all the words of the request (with an accuracy to the form)
150	QDiversity The degree of centralization of the points from which the request is set
151	QBlog Whether the request of blog vocabulary contains
152	XGeoLRlogRelev log (lr, narrowed to the country of the user)
153	XLerfGeoLRlogRelev log (leerflr, narrowed to the country of the user)
154	NonCommercialQuery Binar non -profit request: Querynoncommerciality> 0.965.
155	XLExactMatchesMap The number of links that coincide with the text of the request (other Remap)
156	XLerfNormLRlogRelev Xlerflrlogrelev (normalized for the amount of LerF-wwees of all links, and not for the amount of their source scales)
157	XNonCommNormLRlogRelev Xnoncommlrlogrelev (normalized for the amount of noncomm all links, and not for the amount of their source scales)
158	XNonCommThNormLRlogRelev Link relevance, taking into account the non -profitability of each link and thematic
159	XNonCommLerfNormLRlogRelev Xnoncommelrfnormlrlogrelev (normalized for the amount of noncommlrf-wigles of all links, and not for the amount of their source scales)
160	XNonCommLerfThNormLRlogRelev Link relevance, taking into account the non -profitability of each link, the quality of each link and thematicity
161	Nevasca1 The content of content is not used. ‘Hoost is good (from 0 to 1), calculated on the basis of how many and what hosts the content from this one borrow.
162	Nevasca2 The content of content is not used. ‘Host’s badness’ (from 0 to 1) – is proportional to the number of secondary content on the host.’ The host (from 0 to 1) is proportional to the number of secondary content on the host.
163	LinkAge The average age of links that brought something to LR linkage = min (log (average age of links)/7, 1), 3 years are adopted for 1
164	TLen The length of the page text in the words tlen = map (number of words, 1/400), where map (x, y) = xy / (1 + xy)
165	IsUnreachable The page is unattainable by the links from the muzzle.
166	XLangLRlogRelev LR, taking into account the coincidence of the language and request
167	XLerfLangLRlogRelev LR, taking into account the coincidence of the language of the link and request and accuracy
168	QueryURLClicksFRC the ratio of the number of clicks on this Urlu to all clicks on request
169	QueryDOwnerClicksFRC the ratio of the number of clicks on this Domainid to all clicks on request
170	QueryURLClicksPCTR_copy [Bug: A copy of factor 45] How often they click in this URL for this request – CTR blasting for a correction factor
171	DoppQueryUrlSessionClicksFRCCity What part (on average by the session) from the user Urlov’s user, this URL user, who has been completed to it, is this URL. It is considered to be user sessions.
172	QueryURLClicksPCTR_Reg How often do they click in this URL for this request – CTR blasting for the correction factor, by small regions from Relev_regions.web.txt
173	QueryDOwnerClicksPCTR_Reg How often they click in the URLs of this Domainid for this request – Ctr Domainid to the correction factor, by small regions from Relev_regions.web.txt
174	QueryURLClicksFRC_Reg The ratio of the number of clicks on this Urlu to all clicks on request, by small regions from Relev_regions.web.txt
175	QueryDOwnerClicksFRC_Reg The ratio of the number of clicks on this Domainid to all clicks on request, by small regions from Relev_regions.web.txt
176	QueryURLClicksCombo_Reg Query URL Clicks Combo, in small regions from Relev_regions.web.txt
177	QueryDOwnerClicksCombo_Reg Query Download Clicks Combo, in small regions from Relev_regions.web.txt
178	XLRCatalogRelev LR for catchard descriptions
179	XLRYaCatalogRelev LR to write off in Yandex.Catalog
180	ExactWordOrderLen The length of the maximum coincidence of forms in the text and request
181	ExactWordOrderWeight Weight of maximum coincidence of forms in the text and request
182	WordOrderLen The length of the maximum coincidence in the lemma in the text and request
183	WordOrderWeight The weight of the maximum coincidence by lemma in the text and request
184	LinkMaxAge The maskimal age of a significant accumulation of links that brought something to LR
185	TRp1All Options for relevant factors taking into account the feet of words
186	LRp1All Options for relevant factors taking into account the feet of words
187	TLp1All Options for relevant factors taking into account the feet of words
188	BFexactAll Options for relevant factors taking into account the feet of words
189	BFlemmaAll Options for relevant factors taking into account the feet of words
190	PassageLegacyTR TR of the best passage – how high -quality snippet
191	TxtBM25AttenSyn Tr with discount for suggestions
192	MaxWordHostRank Host Rank according to the most pronounced word of request (usually this is the name of the site)
193	MaxWordHostClicks Domattr clickness for the most expressed word. For example, for all requests in which there is a word Wikipedia click on Wikipedia warders.
194	DomPhraseRank Hostrank by separate words
195	DomPhraseClickRank Domain clickability by words
196	IsForum URL satisfies forum_detector regularly
197	AliceMusicTrackTitleAnnotationMatchWeightedValue The value of the Factor AnnotationMatchweighhedValue for Stryim ALICEMUSIC
198	IsObsolete The URL has an ancient date. Ancient news are recognized. Factor 1 if there is a year in Url <= 2007.
199	TRWithStops Weight of maximum coincidence of forms in the text and request
200	LRWithStops Weight of maximum coincidence of forms in the text and request
201	HasPayments The page has a about ‘payment SMS’.
202	IsLinkPessimised Antispamers pessimized the site – all dynamic link factors are reset. Zerolnk.flt
203	EshopValue Stage of the page
204	PornoValue Pornography of the page
205	TrafgraphOutAll_share_m Remapped mascot feature TrafgraphOutAll_share_m
206	TrafgraphOutAllSE_share_d Remapped mascot feature TrafgraphOutAllSE_share_d
207	TrafgraphOutAllSE_share_m Remapped mascot feature TrafgraphOutAllSE_share_m
208	NoExtClicksShare Remapped mascot feature NoExtClicksShare
209	CountersSearchTraffic1 Search traffic – transitions from search engines to the site (2nd formula)
210	CountersSearchTraffic2 Search traffic – transitions from search engines to the site (2nd formula)
211	DomPhraseYabar Transitions to the site from search engines by individual words, according to the bar
212	AliceMusicArtistNameBclmMixPlainK000001 BCLMIXPLAINK000001 factor
213	QueryUrlLCS The largest total tuning of Urla and request, normalized by the length of Urla
214	OnlyUrl All coincidences are only in the URL, there are no coincidences in the text
215	GeoRelevRegionCity
216	GeoRelevRegionRegion
217	GeoRelevRegionCountry Three levels of coincidence of the geography of the user and page
218	XLRGeoRelevRegionCity
219	XLRGeoRelevRegionRegion
220	XLRGeoRelevRegionCountry Three levels of coincidence of the region of links and request
221	GeoCountryProxim Geographical proximity
222	IsNavQuery Is the request for navigation, on the clicking of the answers
223	MaxWordHostYaBar The most characteristic word of the request corresponding to the site, according to the bar
224	FirstWordHostClicks The clickability of the host according to the first word of the request. Quite often, the first (last) word word is a clear indication of the site on which the information should be sought.
225	AliceMusicArtistNameCMMatchTop5AvgMatch The value of the CMMATCHTCHTOP5AVGMATCH factor for the Stryim ALICEMUSIC
226	QueryDOwnerYabarVisits
227	QueryDOwnerYabarVisitors
228	QueryDOwnerYabarAvgTime The average for users Active continuous time of the user is (in second) on the host pages after the transition on request from the search engine (the factor depends on the pair (request, Domattr)).
229	QueryDOwnerYabarAvgTime2 The average for users Active continuous time of the user is (in second) on the host pages after the transition on request from the search engine (the factor depends on the pair (request, Domattr)). In the inside of the Yandex. Bara/elements/browser counter
230	QueryDOwnerYabarAvgActions The average for users is the number of active actions (clicks, clicks) with the continuous finding of the user on the host pages after the transition on request from the search engine (the factor depends on the pair (request, Domattr)). . In the inside of the Yandex. Bara/elements/browser counter
231	QueryUrlYabarVisits
232	QueryUrlYabarVisitors The number of unique visitors from search engines for a specific request
233	QueryUrlYabarAvgTime The average for users Active continuous time of the user (in second) on the page after the transition on request from the search engine (the factor depends on the pair (request, URL)).
234	QueryUrlYabarAvgTime2 The average for users Active continuous time of the user (in second) on the page after the transition on request from the search engine (the factor depends on the pair (request, URL)). In the inside of the Yandex. Bara/elements/browser counter
235	QueryUrlYabarAvgActions The average for users is the number of active actions (clicks, keystrokes) on the page after the transition on request from the search engine (the factor depends on the pair (request, URL))
236	DssmBertDistillSinsigMseBaseRegChain A pool of logs is marked with BERT trained on Sinsig. DSSM model is trained on this pool using BaseregionChain
237	DssmBertDistillRelevanceMseBaseRegChain A pool from PRS logs is marked using BERT, trained for relevance. DSSM model is trained on this pool using BaseregionChain
238	AliceMusicArtistNamePerWordCMMaxMatchMin PERWORDCMMAXMATCHMIN Factor value for Alicemusic Stryim
239	AliceMusicArtistNameAttenV1_Bm15_K05 The value of the factor attenv1_bm15_k05 for the Stryim ALICEMUSIC
240	AliceMusicAlbumTitleAnnotationMaxValueWeighted The value of the factor annotationmaxvalueEWEEGTED for Stryim ALICEMUSIC
241	IsForeignQuery Request is not in Russian
242	IsForeignCluster foreign cluster document
243	PageRegionSizeIn The size of the page of the page
244	PageRegionInvSizeIn The factor is inversely proportional to the size of the page region
245	QueryRegionSize The size of the region of the request
246	QueryRegionInvSize The factor is inversely proportional to the size of the regional region
247	GeoGeometryProxim The geographical proximity of the user and the site
248	RingsHostRankBadnessOld Characterizes the promotion of the site with ling rings. Value is the share of external links that are included in the lingon rings and battleships.
249	YabarHostVisitors The number of unique visitors, remarks exponentially
250	YabarHostSearchTraffic The share of traffic from search engines
251	YabarHostInternalTraffic The share of suits to the site is not by links (set with hands or from bookmarks)
252	YabarHostAvgTime average for users Active continuous time for user finding (in sec) on the host pages
253	YabarHostAvgTime2 The average for users Active continuous time of the user (in second) on the pages of the host. In the inside of the Yandex. Bara/elements/browser counter
254	YabarHostAvgActions The average for users is the number of active actions (clicks, clicks) with the continuous finding of the user (in second) on the pages of the host.
255	YabarHostBrowseRank Implementation of the algorithm described in the article ((http://wiki.yandex-team.ru//h.yande...UULYUULYUULYUULYUULYUULYUULYUULYUUP032-LIUUUU .pdf http://research.microsoft.com/en-us/people/tyliu/fp032-liu.pdf))
256	YabarUrlVisits Varla’s attendance according to I-Bara
257	YabarUrlVisitors The number of unique visitors to Urla
258	YabarUrlAvgTime The average for users time is the user on the page. It is read as the difference between neighboring transitions.
259	OwnerSatisfied4Rate This is the SEA factor = s4_r/ (k_r+10) where S4_R is the number of clicks> 180 sec, k_r – the total number of clicks. It is considered taking into account reformalization.
260	OwnerSatisfied4Rate_Reg This is the SEA factor = s4_r/ (k_r+10) where S4_R is the number of clicks> 180 sec, k_r – the total number of clicks. It is considered taking into account reformalization. Localized version
261	UrlQueryVariety The degree of variety of requests for which this Urla click
262	IsCommByKeywords Commercial page by keywords. Not used (depreded)
263	DocIdfSum_broken IDF for various parts of the document, broken, are not used
264	TitleIdfSum_broken IDF for various parts of the document, broken, are not used
265	HeadingIdfSum_broken IDF for various parts of the document, broken, are not used
266	NormalTextIdfSum_broken IDF for various parts of the document, broken, are not used
267	XLRVideoRelev Link factor about the presence of a video on the page.
268	AuxTextBM25 BM25 for the user region for localized queries, for the unflapped in Cuba, is a country. The texts of the queries sent for the regions can be viewed in Relev_regions.txt in the sorcerer
269	AuxLinkBM25 The same for lingonic relevance
270	CommLinksSEOHosts The share of incoming corrupt links. The algorithm for recognition of commercial links is implemented. The factor will be remarked to [0.1] if the share of such links is 50%, otherwise 0. ((http://wiki.yandex-team.ru/svetlanashorina/topseolinks selection of wound sites))))))
271	CommLinksSEOHostsPornoQuery Previous factor multiplied by Pornoquery
272	CommLinksSEOHostsNonComm ComMlinksseohosts factor multiplied by Noncommercialquery
273	TovarCategoryQuery The request mentions the product category. Not used (depreded)
274	TovarCategoryVendor The request mentions a vendor. Not used (depreded)
275	Diversity2 Geographical distribution of the request
276	NightQuery The request is set mainly at night
277	MorningQuery The request is set mainly in the morning
278	DayQuery The request is given mainly in the afternoon
279	EveningQuery The request is set mainly in the evening
280	HourDiversity The severity of the querial tasks at different times of the day
281	LCor Characterizes the frequency of words in links. The factor is large, if the word that played in a lincoat relevance is rare for links.
282	SubqueryThMatchA Coincidence of thematic spectra of request and document. Request themes – the result of work ((http://wiki.yandex-team.ru/evgenijjkroxalev/subquery Rules of the sorcerer Subquerysearch)) The subject of the document is determined by the automatic classifier
283	TRDocQuorum The weight of the words of the request that is in the text
284	LRDocQuorum The weight of the words of the request that is in the Links
285	TRLRDocQuorum The weight of the words of the request that is in the text and links
286	OwnerSDiffClickEntropy Entropy – distribution of clicks
287	OwnerSDiffShowEntropy Entropy – distribution of shows
288	OwnerSDiffCSRatioEntropy Entropy – Distribution of clique/shows.
289	XPornoLRlogRelev Document Porn on the text of Leskok
290	XPornoNormLRlogRelev Document Porn on the text of Leskok, other normalization
291	XPornoQuery Classifier of Porn Causions, another dictionary than Pornoquery
292	AliceMusicAlbumTitleAttenV1_Bm15_K05 The value of the factor attenv1_bm15_k05 for the Stryim ALICEMUSIC
293	GeoCountryCountryProxim The geographical proximity of the country of the site and the country of request
294	UrlDomainFraction Coating domain three -bouqu and request. (Chelyabinsk lottery – Chelloto. We translate a request to translite, find the three -book that are covered (Che, Hel, Lot, Olo), we look at what share of all three -bouquets are covered)
295	UrlPathAndParamsFraction The same as the previous factor, but about the entire Url except the domain
296	SpecificalQuery The request is local-specific. The request is often reformulated with the obvious task of the region. ((https://ml.yandex-team.ru/archive/thread1433892/#Message1433892 more))
297	JokerLen We consider text features, believing that the page title is attributed to each of its proposal, i.e. The distance between the word from Title and any other word 1 sentence. Len is the maximum attitude of words from the request of the text met in some sentence (with attributed Title) in relation to the length of the request. Example [Harms Circus Vertunov] for ((http://wiki.yandex-team.ru//h.yandex.net/?http://WWWWIKILIVRES.info/WIKI/%D0%A6%D %25b8%25D1%2580%25D0%25D0%25A %25BC%25D1%2581%of this document))
298	JokerWeight The ratio of the amount of IDF words in a sentence+Title to all words.
299	ExactJokerLen The same as Jokerlen, in the exact forms
300	ExactJokerWeight The same as Jokerweight, in the exact forms
301	More120SecVisitsNotSearchShare Remapped mascot feature More120SecVisitsNotSearchShare
302	LnkBreak Analogs of the corresponding text factors for links. BM25 from the number of links in which a coincidence occurred.
303	LnkBm25Ex Simple BM25 in the exact form in link texts
304	LnkPairSy The presence of pairs in the links of the words, taking into account synonyms
305	LnkBrkSy The number of links passed the threshold
306	LnkBm25Sy Simple BM25 by links taking into account synonyms
307	VideoQuery Request about the video
308	OwnerClicksPCTR_Reg The owner’s clickness regardless of the request, separately in the regions
309	OwnerSDiffClickEntropy_Reg Entropy is the distribution of clicks. Regionalized
310	OwnerSDiffShowEntropy_Reg Entropy is the distribution of shows. Regionalized
311	OwnerSDiffCSRatioEntropy_Reg Entropy – distribution of clique/shows. Regionalized
312	Adultness equals 2 * NastyContent
313	HostAdultness equals 2 * NastyContent
314	KCHostAdultness always zero
315	IsCom Domna in Zone .com
316	IsUa Domain in the .ua zone
317	IsNotRu Domain is not in the .ru zone
318	XLRMarketRelev LR by links from Yandex.Market
319	Poetry The poetry of the document
320	PoetryQuad The maximum poetry of the quatrain
321	EngLang Document language – English
322	Has2ExactQueryParts The request is completely covered by two exact groups consisting of an exact Match of the words of a contract in a row ((http://wiki.yandex-team.ru/poiskovajaplatform/tr/coveragebygroups about grouping in groups))
323	HasLevensht1QueryFragment There is a group consisting of an Exact Match of the words of the request that covers the request (possibly with a pass, addition or replacement of a word)
324	LargestSyInexactGroup The share of the request, covered by the longest group consisting of any hits (including word forms and synonyms). Possibly with a pass, addition or replacement of a word
325	TimeProfilesMatchWD Characterizes the proximity of temporary profiles of request and documents on business days
326	TimeProfilesMatchWE Characterizes the proximity of temporary profiles of the request and documents on weekends
327	CyrLang The language of the document is Cyrillic
328	GeoRegionalityU Requestful factors – the result of work ((http://wiki.yandex-team.ru/jandeksp...ayaformula/tekushhiekomponenty/georegionality classifier of geolocalization of the request)))))))))))))
329	GeoRegionalityR R- Georelevan – regional results in the issuance could be useful, but nothing more
330	GeoRegionalityV V- geovital – regional issuance is of fundamental importance
331	UrlHasNoDigits There are no numbers in Urla
332	AliceMusicTrackArtistNamesAllWcmMaxMatch ALLWCMMAXMatch factor
333	AliceMusicTrackAlbumTitleCosineMatchMaxPrediction The value of the cosinematchmaxprediction factor for the Stryim ALICEMUSIC
334	SynS1 Show how much the text is unnatural from the point of view of the Russian language. Assessment of how much the text of the document can be considered as a generated synonymizer or automatic. ((http://wiki.yandex-team.ru/jandeksp...a/tekushhiekomponenty/antispam?v=1il#h58953-2 more))
335	SynFLremap1 Show how much the text is unnatural from the point of view of the Russian language. Assessment of how much the text of the document can be considered as a generated synonymizer or automatic. ((http://wiki.yandex-team.ru/jandeksp...a/tekushhiekomponenty/antispam?v=1il#h58953-2 more))
336	SynFLremap2 Show how much the text is unnatural from the point of view of the Russian language. Assessment of how much the text of the document can be considered as a generated synonymizer or automatic. ((http://wiki.yandex-team.ru/jandeksp...a/tekushhiekomponenty/antispam?v=1il#h58953-2 more))
337	OwnerSessNormDuration ND/K normalized time to click
338	UrlSessNormDurRate nd/i
339	QueryDOwnerSessNormDuration CONTRY / K
340	QueryDOwnerWeightClick w/k
341	QueryDOwnerOnlyClickRate o/i
342	QueryDOwnerClickSummary Selected formula
343	QueryDOwnerSatisfied4Rate r_s4b/(r_k + 10)
344	SyntQuality Does the request have a complete syntactic analysis
345	PageDate The date of the document that is registered on the page is remarkable
346	VisitsPVisitors Remapped mascot feature VisitsPVisitors
347	RingsHostRankBadness2 Additional factors about the promotion of the site with ling rings, ((http://wiki.yandex-team.ru/jandeksp.../tekushhiekomponenty/antispam?v=181r#h58953-4))
348	RingsHostRankBadness3 Additional factors about the promotion of the site with ling rings, ((http://wiki.yandex-team.ru/jandeksp.../tekushhiekomponenty/antispam?v=181r#h58953-4))
349	RingsHostRankBadness4 Additional factors about the promotion of the site with ling rings, ((http://wiki.yandex-team.ru/jandeksp.../tekushhiekomponenty/antispam?v=181r#h58953-4))
350	HasTextPos The document has textual relevance
351	QSegmentsBM25 BM25, where the selected segments of the request act as ‘words’
352	QSegmentsWeight ‘Weight’ of the segments of the request in the text
353	SynPercentBadWordPairs An indicator of the unnaturalness of the text from the point of view of the Russian language. The number of bad pairs of words in the text, transferred to the segment [0.1] according to the Z/(Z+10) formula
354	SynNumBadWordPairs The proportion of bad steam among all found in the table: Z/(X+1), where Z is the number of bad couples in the text, and X is (http://wiki.yandex-team.ru/evgenijgrechnikov/testsynonimizers of 2000-navigable )) steam
355	NumLatinLetters The number of Latin letters in the text (not counting the markings) driven into [0.1] formula n/(n+100)
356	RingsHostRankBadness1 Additional factors about the promotion of the site with ling rings, ((http://wiki.yandex-team.ru/jandeksp.../tekushhiekomponenty/antispam?v=181r#h58953-4))
357	DocIdfSumFixed Previous factors – fixed
358	TitleIdfSumFixed Previous factors – fixed
359	HeadingIdfSumFixed Previous factors – fixed
360	NormalTextIdfSumFixed Previous factors – fixed
361	QueryURLClicksCombo factor cunningly combined from FRC and Pseudo-CTR
362	QueryDOwnerClicksCombo factor cunningly combined from FRC and Pseudo-CTR
363	LRAmortizedByAge Link relevance with pessimization for great age Link
364	RusWordsInText The number of words in the text (the word is what the lemmeter selected) is displayed in [0.1] according to the formula x/(x+a)
365	RusWordsInTitle The number of words of the Russian language in the title
366	MeanWordLength The average length of the word
367	PercentWordsInLinks The percentage of the number of words inside the tag <a> .. </a> from the number of all words
368	PercentVisibleContent The percentage of the number of words outside the tags (outside the brackets <>) from the number of all words
369	PercentFreqWords The percentage of the number of words, which are 200 the most frequent words of the language, from the number of all words of the text
370	PercentUsedFreqWords The number used in the text 500 of the most popular words of the language, divided by 500
371	TrigramsProb Logarithm of average geometric probabilities of trigrams in the text. (the probability of a trigram – the number of its meetings in the text, divided by the number of all trigrams) is displayed in [0.1] according to the formula -x (x+a)
372	TrigramsCondProb Logarithm of the average geometric conditional probabilities of trigrams. The conditional probability of a trigram is its probability, divided by the probability of a bigram from the first two words
373	DoppDOwnerPCTR The analogue of the QueryDownerClickSpCTR factor differs from it in that the requests are normalized by doppelgage (details of such normalization -((http://staff.yandex-team.ru/finder Andrei Plakhov)), code/yandex/doppelganges)
374	DoppDOwnerPCTR_Reg The analogue of the QueryDownerClickspCTR factor differs from it in that the requests are normalized according to doppelgage (details of such normalization -((http://staff.yandex-team.ru/finder Andrei Plakhov)), code/yandex/Doppelganges). Localized to Relev_regions.web.txt
375	DoppUrlPCTR The analogue of the QueryurlClickSpCTR factor differs from it in that the requests are normalized by doppelgagers (details of such normalization – ((http://staff.yandex-team.ru/finder Andrei Plakhov)), code – Yandex/Doppelganges)
376	DoppUrlPCTR_Reg The analogue of the QueryurlClickSpCTR factor differs from it in that the requests are normalized by doppelgage (details of such normalization – ((http://staff.yandex-team.ru/finder Andrei Plakhov)), code – Yandex/Doppelganges). Localized to Relev_regions.web.txt
377	UrlBM25 BM25 on URL’U
378	HasBigPicture The page has a big picture
379	MatrixNet Matrixnet is applied to all factors – formula (tg_unized – to prevent the entrance to any formulas)
380	DaterAge The difference between the current date and the date of the document defined by the dates, 1 – the date of the document is equal to the current, 0 – the document of 10 years or more, if the date is not defined, equal to 0. Attention! ((1 – dateraage)*60)^2 = age of the page In days.
381	IsHardPessimization Hard pessimization (AKA PR = 0), binary factor, is considered in Antispam
382	CInDegree1 The host factors determine the sites screwed by the links-the second and third incoming degrees ((http://wiki.yandex- team.ru/jandekspoisk/kachestvopoiska/obshayafformula/
383	CInDegree2 The host factors determine the sites screwed by the links-the second and third incoming degrees ((http://wiki.yandex- team.ru/jandekspoisk/kachestvopoiska/obshayafformula/
384	NumNonRussianLinks The number of incoming links without Russian letters. Remembrance.
385	TextMaxForms The maximum number of forms in all words of the request is max in all words of the request request_form_dl_lov/64
386	TextWeightedForms The sum of the number of forms balanced by the scales of words – the amount in all words of the request of the number_form_dly_lov/64*weight_lov; REMAP species x/(1 + x).
387	TextForms The unwarmed amount of the number of forms is the amount in all words of the request of the number_form_dl_lov/64/number_lov_
388	LinkMaxForms The maximum number of forms in all words of the request
389	LinkWeightedForms Summer of the number of forms balanced by scales
390	LinkForms Undested amount of the number of forms
391	TR_W1 Analogues of the factors of the same name, the weight of the word = 1
392	XLR_W1 Analogues of the factors of the same name, the weight of the word = 1
393	TextBM25_Fm_W1 Analogues of the factors of the same name, the weight of the word = 1
394	TextBM25_Sy_W1 Analogues of the factors of the same name, the weight of the word = 1
395	LinkBM25_W1 Analogues of the factors of the same name, the weight of the word = 1
396	TLBM25_W1 Analogues of the factors of the same name, the weight of the word = 1
397	QSegmentsBreaks Request segments are parts of the request, which in themselves are frequency requests. The factor shows how much the segments are in the text. value 0 – all words are found only within the framework of the indicated segments, 1 – all the entries break segments
398	AliceMusicTrackLyricsCMMatchTop5AvgMatch The value of the CMMATCHTCHTOP5AVGMATCH factor for the Stryim ALICEMUSIC
399	NumeralsPortion The share of different parts of speech in the text. The share of numerals (among all words that managed to recognize part of the speech)
400	ParticlesPortion The share of particles
401	AdjPronounsPortion The share of pronoun adjectives
402	AdvPronounsPortion The proportion of pronoun nouns
403	VerbsPortion The share of verbs
404	FemAndMasNounsPortion The share of words that can be both masculine nouns and nouns of the feminine, but not of the middle kind, among all nouns (examples: ‘hummingbirds’ are an example of an indefinite kind that can be determined in two ways, ‘Alexander’ is homonymy).
405	LinkQualityFixed Quality of incoming links (hauser classifier) corrected
406	HasLinkQualityFixed Considered Linkqualy for this page or not (did not think, if there are few links) corrected
407	NewLinkQualityFixed Quality classifier of incoming links 2 corrected
408	IsOrg The request is the name of the organization (example: Gazprom, Gazprom) ((http://wiki.yandex-team.ru/arsengadzhikurbanov/warees Description))
409	AliceMusicArtistNameCMMatchTop5AvgMatchValue The value of the CMMATCHTCHTOP5AVGMATCHVALUE factor for Stryim ALICEMUSIC
410	LongestText The size of the largest text segment (from the factor [18] puretext)
411	SmartUkrainian
412	SmartBelorussian
413	LRWithoutRare Link relevance without taking into account rare words
414	DifferentInternalLinks The number of different internal links to the page
415	HasDeterminedCities The city is defined for the site
416	GeoRegionalityUNew Requestful factors – the result of the work ((http://wiki.yandex-team.ru/poiskova...a/zaprosnyjefefactory/localizovannyjezaprosya classifier of the request of the request)) – a new version of factors [328] – [328] – [328]: u – u – u – u – u – u – uceleless sites the request is meaningless;
417	GeoRegionalityRNew Запросные факторы – результат работы ((http://wiki.yandex-team.ru/PoiskovajaPlatforma/Lingvistika/ZaprosnyjeFactory/LocalizovannyjeZaprosy классификатора геолокализованности запроса)) – новая версия факторов [328]-[330]: R – георелевантные – региональные результаты в issuing could be useful, but nothing more;
418	GeoRegionalityVNew Requestful factors – the result of work ((http://wiki.yandex-team.ru/poiskova...a/zaprosnyjefefactory/localizovannyjezaprosya classifier of the request of the request)) – a new version of factors [328]: Vegetable fundamental importance.
419	AliceMusicArtistNamePerWordCMMaxPredictionMin The value of the perwordcmmaxpredictionmin factor for Stryim ALICEMUSIC
420	UkrainPageRank Ukrainian Page Rank
421	QClassDownload = 1 – v. Download formula. Class requests: download/watch online/play/photo/listen
422	QClassBrandnames The result of the classifier of the request – in the request there are words from the corresponding dictionary. brand
423	QClassDisease Medication Dictionary
424	QClassKak question
425	QClassMoscow Specific request for Moscow
426	QClassOAO organization
427	QClassPorno porn
428	QClassTravel trips
429	VideoRating The popularity of the video roller comes from the video
430	PeriodicLinkDatesPercent The frequency of links to the site
431	LinkAlmostPeriod The number of almost-periodic links
432	QDOwnerStatPower The number of Owner shows on request, normalization x/(100 + x).
433	QUrlStatPower The number of URL shows on request, normalization x/(100 + x).
434	HasLiRuCounter The presence of a LiveInternet meter
435	OwnerReqsPopularity The popularity of Owner is in requests
436	DssmYaMusicASREarlyBindingCe DSSM model with early binding, trained on reforming and learned by ASR hypotheses of musical requests for Alice
437	DssmBertDistillSinsigCeCountryRegChain A model trained on a PRS-Law PRS to predict BERT, trained on sinsig_ce with threshold value 0.5, using a chain of regions to the country
438	DssmYaMusicEarlyBindingCe DSSM model with early binding, trained on reforming and learned on musical requests for Alice
439	SecondIndegDistrXi Eleven factors based on the statistical properties of the distributions of incoming degrees of peaks referring to the fixed top of the hostographer. ((Http://wiki.yandex-team.ru/jandekpoisk/kachestvopoiska/obshayaformula/tekushhiekmponenty/HostdDEGRE)
440	PiracyDetectorPredict The value of the pirate detector calculated in the hippo.
441	AliceMusicUrlTypeIsAlbum Type of canonized Urla Yandex Music – Album
442	FirstValidTs10Days It is considered as (10-x) where X is the return of the document in days (continuously) regarding the validity time of the document in Samovar
443	HostInQuery The host of the document is recognized in the request
444	VitalHostInQuery URL consists only of the host, which is recognized in the request
445	YandexNewsStoryUrl URL is the plot of Yandex News
446	RcSpylogUrlRationalSigmoidD1T240 URL feature computed from rapid clicks spy_log counters with decay of 1 day
447	RcSpylogUrlRationalSigmoidD1T240Frozen URL feature computed from rapid clicks spy_log counters with decay of 1 day
448	RcSpylogUrlRationalSigmoidD0_5T30 URL feature computed from rapid clicks spy_log counters with decay of 0.5 days
449	RcSpylogUrlRationalSigmoidD0_5T30Frozen URL feature computed from rapid clicks spy_log counters with decay of 0.5 day
450	Timestamp They are considered as (80 – x) / 80, where X is the age of the document in the watch. Factors make sense only for the fast -button base (the last 80 hours). Not used in ranking. Used in disconnecting.

Okumaya devam et...

Hoş Geldin, Ziyaretçi!

SEO Dünyasının En Büyük Haberi: 1922 Farklı SEO Sıralama Faktörü Sızdırıldı.

asciyamagi

Tüccar