Tag: TG_NOT_01

The value of the news detector calculated in the Hippo. Always 0 with a detector value less than the threshold.

The value of the commerce detector calculated in the Hippo.

Matrixnet is applied to all factors - formula (tg_unized - to prevent the entrance to any formulas)

The value of the pirate detector calculated in the hippo.

Medical host quality for new marks.

Medical host quality for new marks for experiments.

Finance or law host quality for new marks.

Finance or law host quality for new marks for experiments.

Finance or law host quality for new marks.

Finance or law host quality for new marks for experiments.

Age of rapid clicks spy_log update, in seconds

The value of the chopped commerce detector, calculated in the hippo.

The value of the health detector calculated in the Hippo.

User outflow coefficient from the search after a visit to the site

The value of the conversion of the request calculated in the Hippo.

DSSM Prediction of the probability of URL + Title that the document is an overlap.

The value of PURCHASETOTALPredict, calculated in the Hippo.

Requestwith120d3ClickpartPredict value, calculated in the Hippo.

Predict SOS.DSSM models by URL + Title.

Med.DSSM Predictions URL + Title models.

Predict Cruelty.dssm URL + TITLE models.

Prediction of Med_with_Trash.DSSM (Medic. Document model with Tresh Valley in Lern) Models for URL + Title.

Prediction FIN_LAW_WITH_TRASH.DSSM (Fin-Jur. Document model with a tresh valve in Lern) Models for URL + Title.

Neural model of content quality for medical subjects

Neural model of content quality for medical subjects (for ex -)

Neural model of content quality for financial and legal topics

Neural model of content quality for financial and legal topics (for exposures)

Neural model of content quality for SOS topics

Neural model of content quality for SOS subjects (for ex -)

DSSM prediction (URL + Title), trained for the Page_QUALYY signal and implemented in RTHUB, the first slot.

Neural document model for finding unexpected tin

The average freshness of the host of the host in 30 days

'Random' factor for commercial sites.

Neuron document model for finding unexpected tin (for ex -)

Count of utterance hypothesises from ASR

Max count of words in utterance hypothesises from ASR

Min count of words in utterance hypothesises from ASR

Average count of words in utterance hypothesises from ASR

Standard deviation of words count in utterance hypothesises from ASR

Count of words in winner utterance hypothesis from ASR

Max length of utterance hypothesises from ASR

Min length of utterance hypothesises from ASR

Average length of utterance hypothesises from ASR

Standard deviation of utterance hypothesises lengths from ASR

Length of winner utterance hypothesis from ASR

Number of speakers deduced from ASR hypothesises

Count of music hosts in search results

Count of video hosts in search results

DCG@5 of music hosts positions

DCG@5 of music hosts positions

Overall DCG of music hosts positions

Overall DCG of video hosts positions

The value of the news detector calculated in the Hippo. Always 0 with a detector value less than the threshold.

The value of the pirate detector calculated in the hippo.

The value of the commerce detector calculated in the Hippo.

The value of the chopped commerce detector calculated in the hippo.

The value of the health detector calculated in the Hippo.

The value of Purchasetotalpredict, calculated in the Hippo.

Requestwith120d3ClickpartPredict value, calculated in the Hippo.

The value of the conversion of the request calculated in the Hippo.

Classifier of one product in the request

Classifier of several goods in the request

The value of the Proxima DCG-5, calculated in the hippo.

Prediction of the classifier that the request is a legal

Prediction of the classifier that the request is financial

The prediction of the classifier is that the request of SOS topics

The prediction of the classifier is that the request is white (that is, it is not worth showing tin on it)

Prediction of the classifier to especially commercial requests

Classifier of a request for equipment repair services: office, household, computers, phones

Prediction of the requesting classifier of violence

Prediction of the requesting classifier of weapons or drugs

Sum of host VIDEOness of search results, negative value means anti-VIDEOness

Sum of host MUSICality of search results

Sum of host BOOKishness of search results

Number of wiki page shows per 2 months according to Wikipedia data

Number of detected documents in source

CTR Web sum of the first 4 elements

Sum Ctr Web 5-9 elements

The amount of the CTR Web Foreign first 4 elements

CTR Web Foreign 5-9 elements

Sum of host VACANCYty of search results

Number of offers in turkish market (deprecated due to closing turkish market)

Minimum price in TL without kopecks in turkish market (deprecated due to closing turkish market)

Maximum price in TL without kopecks in turkish market (deprecated due to closing turkish market)

Unbiased variance of price in turkish market (deprecated due to closing turkish market)

Number of shops with offers in turkish market (deprecated due to closing turkish market)

Number of categories with offers in turkish market (deprecated due to closing turkish market)

Number of offers from 'good' shops in turkish market (deprecated due to closing turkish market)

Number of offers from 'bad' shops in turkish market (deprecated due to closing turkish market)

Duplicate of FI_ADRESA_COMM_MX

The number of documents found in the Web-Base

The number of documents found in the database of the fast -butter

The number of documents found in Realtime

QuickDocCount * 100 / WebDocCountFresh

Peak size (in watches), 50 top documents are taken into account from each fast -butter machine

The total number of documents from the large base that have passed on Fastrank

The share of documents from a large base that have been created on Fastrank created in recent months

What percentage of fast documents came from the domain, which found the most results

What percentage of fast documents came from the second (according to the number of results) domain

How long have long been read from the disk database of fast -butter

The number of words in the request

The popularity of the request. The result of the sorcerer's work

The request mentions the commodity category

The request mentions vendor

How much was the speed of this request before in the database of a fast -butter, the average in 2 weeks

How much was used to be in this request in Realtime, average in 2 weeks

Number of news topics with entity from query doppelganger for last 6 months

Timestamp launching basic Fasttier

Number of documnets prepared for News Wizard

Number of videos in News Wizard

Number of Yandex.News stories in News Wizard

1 if NewsWizard is a single story one, -1 else

Ratio between clicks on fresh results in last half hour and hour

Ratio between fresh surplus and total number of queries

Ratio between clicks on news results in last half hour and hour

Ratio between news surplus and total number of queries

Same as QuickClicksLastHourRatio, calculated using doppelgangers

Same as QuickSurplusToQueriesRatio, calculated using doppelgangers

Same as NewsClicksLastHourRatio, calculated using doppelgangers

Same as NewsSurplusToQueriesRatio, calculated using doppelgangers

The linear combination of found in the last 5 hours, day and 3 days, divided into the total number of documents found for which PassagelegacyTR is not 0, only for Videop and Videoquick sources

afisha wizard tokens related to timetable

afisha wizard tokens realted to watching intent

afisha wizard tokens related to event type(comedy, acttion, etc.)

afisha wizard tokens related to similar intent(review, i.e.)

number of documents found by afisha source

afisha source generated event rating

number of places where the event is on

total number of the given event in all places for the period available to source

how many days to start if negative, or how many days from start if positive

how many days to end if positive, how many days after last event if negative

number of uniq events for the given place

total number of events for the given place

afisha host classifier

number of different event types that can be held at the place (exhibitions, movies)

total number of places having any of the event types with the given place

host classifier for auto vertical

Adresa results max relevance

Adresa Results Min Relevance

Adresa results average relevance

Adresa number of results

CommercialMx rule commerciality

Max offers number in one category (deprecated due to closing turkish market)

Number of categories with more than one relevant offers (deprecated due to closing turkish market)

Number of categories with more than two relevant offers (deprecated due to closing turkish market)

Number of models for offer (deprecated due to closing turkish market)

The time of the day

VideoLogProdWordsFRC

VideoLogProdWordsCTR

VideoLogProdWordsCCTR

VideoLogProdWordsSTR

VideoLogProdWordsCSTR

VideoLogProdWordsContrast

VideoMaxWordsContrast

MusicLogProdWordsFRC

MusicLogProdWordsCTR

MusicLogProdWordsCCTR

MusicLogProdWordsSTR

MusicLogProdWordsCSTR

ImagesLogProdWordsFRC

ImagesLogProdWordsCTR

ImagesLogProdWordsCCTR

ImagesLogProdWordsSTR

ImagesLogProdWordsCSTR

ImagesLogProdWordsContrast

ImagesMaxWordsContrast

Number of documents in dg grouping

Number of documents in dgq grouping

Logified Linear text classifier prediction learned on images production pool with positives and wins factor one

Linear text classifier prediction learned on images production pool with positives and wins factor two

Linear text classifier prediction learned on images production pool with positives and wins factor four

Linear text classifier prediction learned on video production pool with positives and wins factor one

Linear text classifier prediction learned on video production pool with positives and wins factor two

Linear text classifier prediction learned on video production pool with positives and wins factor four

Linear text classifier prediction learned on video production pool with positives and wins factor four

Mean surf depth nodes gradient

Min surf depth nodes gradient

Max surf depth nodes gradient

Mean surf depth nodes gradient disp

Min surf depth nodes gradient disp

Max surf depth nodes gradient disp

Mean surf depth nodes leaf length

Min surf depth nodes leaf length

Max surf depth nodes leaf length

Mean surf depth nodes leaf length90

Min surf depth nodes leaf length90

Max surf depth nodes leaf length90

Mean surf depth time gradient

Min surf depth time gradient

Max surf depth time gradient

Mean surf depth time gradient disp

Min surf depth time gradient disp

Max surf depth time gradient disp

Mean surf depth time leaf length

Min surf depth time leaf length

Max surf depth time leaf length

Mean surf depth time leaf length90

Min surf depth time leaf length90

Max surf depth time leaf length90

Mean surf nodes time gradient

Min surf nodes time gradient

Max surf nodes time gradient

Mean surf nodes time gradient disp

Min surf nodes time gradient disp

Max surf nodes time gradient disp

Mean surf nodes time leaf length

Min surf nodes time leaf length

Max surf nodes time leaf length

Mean surf nodes time leaf length90

Min surf nodes time leaf length90

Max surf nodes time leaf length90

Mean surf nodes hangs gradient

Min surf nodes hangs gradient

Max surf nodes hangs gradient

Mean surf time

Min surf time

Max surf time

Mean surf nodes

Min surf nodes

Max surf nodes

Mean surf depth

Min surf depth

Max surf depth

Mean surf hangs

Min surf hangs

Max surf hangs

Mean surf downloads

Min surf downloads

Max surf downloads

Max CTR for all words in request per month

Average CTR for all words in request per month

Remapped uatraits BrowserEngine value

Remapped uatraits OSFamily value

Accumulate value of fresh hosts feature, based on fresh surplus, which was calculated for each host with shows threshold 50

VideoQuickDocCount * 100 / VideoDocCount

Minimal difference between request time and document time for top-5 documents from d:fresh grouping

Maximal difference between request time and document time for top-5 documents from d:fresh grouping

Average difference between request time and document time for top-5 documents from d:fresh grouping

Decayed counter for this query for last day, using doppelgangers instead of exact query

Number of such requests (with same vnorm_dopp) during 1 hour divided by number of requests during 8 hours

The linear combination of found in the last 5 hours, day and 3 days, divided into the total number of documents found for which PassagelegacyTR is not 0, only for video sources

Address snippet count in the top 10 web results.

Items (orgs) count of the top address snippet.

First address snippet position in top 10 web results.

Same as QuickClicksLastHourRatioDopp, collect logs for 5 minutes before each aggregation

Same as QuickSurplusToQueriesRatioDopp, collect logs for 5 minutes before each aggregation

Same as NewsClicksLastHourRatioDopp, collect logs for 5 minutes before each aggregation

Same as NewsSurplusToQueriesRatioDopp, collect logs for 5 minutes before each aggregation

Ratio between clicks on images results in last half hour and hour, collect logs for 5 minutes before each aggregation

Ratio between images surplus and total number of queries, collect logs for 5 minutes before each aggregation

Ratio between clicks on video results in last half hour and hour, collect logs for 5 minutes before each aggregation

Same as NewsSurplusToQueriesRatio, collect logs for 5 minutes before each aggregation

Number of clicks on documents from VIDEOQUICK divided by total number of clicks for given query during last 8 hours

Number of clicks on documents from VIDEOQUICK divided by number of shown documents from VIDEOQUICK for given query during last 8 hours

Number of clicks on documents from VIDEO divided by number of shown documents from VIDEO for given query during last 8 hours

Number of corrected clicks on documents from VIDEOQUICK divided by total number of corrected clicks for given query during last 8 hours

Number of corrected clicks on documents from VIDEO divided by number of corrected shows for documents from VIDEO for given query during last 8 hours

Number of clicks on documents from VIDEO divided by number of shown documents from VIDEO for given query during last hour

For each SERP with given query in last 8 hours, calculate CTR for VIDEOQUICK and accumulate. Same for VIDEO source. Ratio of this values is the value for this factor

Surplus on following data: block of fresh videos is a win block, each non-fresh video is loss block. One win (or loss) is a click on video from a block. Factor is a sum for each query sum for each block of surplus value for last hour.

Surplus on following data: block of fresh videos is a win block, each non-fresh video is loss block. One win (or loss) is a click on video from a block. Factor is a sum for each query sum for each block of surplus value for last 8 hours.

Surplus on following data: block of fresh videos is a win block, each non-fresh video is loss block. One win (or loss) is a click on video from a block. Factor is a sum for each query mean for all blocks of surplus value for last 8 hours.

Surplus on following data: block of fresh videos is a win block, each non-fresh video is loss block. Win (or loss) is a view depth of videos from a block. Factor is a sum for each query sum for all blocks of surplus value for last 8 hours.

Surplus on following data: block of fresh videos is a win block, each non-fresh video is loss block. Win (or loss) is a dwell time of videos from a block. Factor is a sum for each query median for all blocks of surplus value for last 8 hours.

Surplus on following data: block of fresh videos is a win block, each non-fresh video is loss block. Win (or loss) is a view duration of videos from a block. Factor is a sum for each query median for all blocks of surplus value for last 8 hours.

Average value of factor Bclm2 of top 10 docs from VIDEOQUICK source, divided by same value from VIDEO source

Number of orgs with selected rubric in orgs base.

Mx model value of rubric extension quality.

Same as QuickClicksLastHourRatioDoppFixed, but use data only from mobile search

Same as QuickSurplusToQueriesRatioDoppFixed, but use data only from mobile search

Rankning relevance divide by relevance scale (1000000) for first doc in WEB answer

Entity search rearrange serp fact score

Entity search rearrange serp score

Mean view time of docs from VIDEO source (last 1 hour).

Mean view time of docs from VIDEOQUICK source (last 8 hours).

Views of docs from VIDEO source (1 hour).

Shows of docs from VIDEOQUICK source (8 hours).

EntitySearch card facts count

EntitySearch card description length

EntitySearch card description source code

Metafator, prediction of WINS on other factors

Metafator, Losses prediction on other factors

Metafator, prediction of the total DwellTime for other factors

Loss per show for associations video wizard for video norm dopp for 90d.

Total Surplus for Associations Video Wizard for Video Norm Dopp for 90D.

Clicks per show for associations video wizard for video norm dopp for 90d.

Refuses per show for associations video wizard for video norm dopp for 90d.

Clicks after wizard-click per show for associations video wizard for video norm dopp for 90d.

Refuses per click after for associations video wizard for video norm dopp for 7d.

Win per show for associations video wizard for video norm dopp for 7d.

Views per show for associations video wizard for video norm dopp for 90d.

Loss per show for projects video wizard for video norm dopp for 90d.

Total surplus for projects video wizard for video norm dopp for 90d.

Clicks per show for projects video wizard for video norm dopp for 90d.

Surplus per show for projects video wizard for video norm dopp for 7d.

Win per show for projects video wizard for video norm dopp for 7d.

Number of higher wizard-clicks for projects video wizard for video norm dopp for 90d.

Views per show for projects video wizard for video norm dopp for 90d.

Total LVT when we have higher wizard for projects video wizard for video norm dopp for 90d.

Loss per show for delayed view video wizard for video norm dopp for 90d.

Total surplus for delayed view video wizard for video norm dopp for 90d.

Clicks per show for delayed view video wizard for video norm dopp for 90d.

Win per show for delayed view video wizard for video norm dopp for 90d.

Loss per show for related query video wizard for video norm dopp for 90d.

Clicks per show for related query video wizard for video norm dopp for 90d.

Loss per show for related query video wizard for video norm dopp for 7d.

Win per show for related query video wizard for video norm dopp for 90d.

Total surplus for related query video wizard for video norm dopp for 90d.

Loss per show for porn actresses video wizard for video norm dopp for 90d.

Total surplus for porn actresses video wizard for video norm dopp for 90d.

Clicks per show for porn actresses video wizard for video norm dopp for 90d.

Win per show for porn actresses video wizard for video norm dopp for 90d.

Max value of video clickadd_new fml for top-1 video results

Max value of video clickadd_new fml for top-4 video results

Avg value of video relevance_new fml for top-1 video results

Avg value of video relevance_new fml for top-4 video results

The number of transitions to the partner of Ya. Traveling for the last week

The number of transitions to the partner of Ya. Traveling over the past 4 weeks

The number of transitions to the partner of Ya. Traveling over the past 12 weeks

The number of hotel armor through the Ya. Traveling in the last week

The number of hotel armor through the Ya. Traveling over the past 4 weeks

The number of hotel armor through the Ya. Traveling in the last 12 weeks

Hotel rating on J.

Average price per night in rubles over the past 4 weeks

Average revenue overnight in rubles over the past 4 weeks

Rating on Booking.com

Median prices per night over the past 4 weeks

Hits for FB partner

Visits for FB partner

The average user stay on the FB partner page

The average availability of the hotel in search of the last 3 days, the description see https://st.yandex-team.ru/hotels-3460

The average availability of the hotel in search of the last 4 weeks, the description see https://st.yandex-team.ru/hotels-3460

The number of interactive searches of the hotel, like 1orga, from the hotel sorcerer in the last 4 weeks (Hotels-3784)

The number of interactive searches of the hotel, as similar, over the past 4 weeks (Hotels-3784)

The number of interactive searches of the hotel from a carousel from a sickle or cards over the past 4 weeks (Hotels-3784)

Total conversion by partners

Average conversion by partners

The number of bookings on Booking.com

The number of hits on Booking.com

Predicted number of clicks for organization

Predictated amount of reservation of rganization

Price rating for sorting by price (more expensive)

Factor for experiments on ranking #1

Factor for experiments on ranking #2

Factor for experiments on ranking #3

Factor for experiments on ranking #4

Factor for experiments on ranking #5

Factor for experiments on ranking #6

Factor for experiments on ranking #7

Factor for experiments on ranking #8

The most likely floor of the user

Weighted floor (waist) user

The most likely age group of the user

Weighted age group (waist) of the user

The most likely user income category

Weighted category of income (waist) user

Personal Skir Organization for the User

L1 top position

Matrixnet is applied to all factors - formula

Prediction of a linear model at L2 Stages

Prediction of a linear model at L3 Stages

Prediction of a linear model at L2 Stages

Prediction of a linear model at L2 Stages

Prediction of a linear model at L3 Stages

Prediction of a linear model at L3 Stages

Watchlog Counter 2 0 Green 0 Dwelltime 0 Days 2, the number of events in user history

Watchlog Counter 2 0 Green 0 Dwelltime 0 Days 7, the number of events in user history

Watchlog COUNTER 1 1 green 0 dwelltime 0 days 14

Watchlog Counter 2 0 Green 0 Dwelltime 0 Days 14, the number of events in user history

Watchlog COUNTER 1 0 green 0 dwelltime 0 days 30

Watchlog COUNTER 1 1 green 0 dwelltime 0 days 30

Watchlog Counter 2 0 Green 0 Dwelltime 0 Days 30, the number of events in the history of user

Watchlog CLUSTER COUNTER 9 0 green 0 dwelltime 0 days 30: distance from right url to cluster9 in base clustering

Watchlog COUNTER 1 0 green 0 dwelltime 0 days 60

Watchlog COUNTER 1 1 green 0 dwelltime 0 days 60

Watchlog Counter 2 0 Green 0 Dwelltime 0 Days 60, the number of events in the history of user

Watchlog CLUSTER 1 0 green 0 dwelltime 0 days 90

Watchlog CLUSTER 1 1 green 0 dwelltime 0 days 90

Watchlog CLUSTER 1 2 green 0 dwelltime 0 days 90

Watchlog CLUSTER 1 6 green 0 dwelltime 0 days 90

Watchlog CLUSTER 1 7 green 0 dwelltime 0 days 90

Watchlog CLUSTER 2 4 green 0 dwelltime 0 days 90

Watchlog CLUSTER 2 6 green 0 dwelltime 0 days 90

Watchlog COUNTER 1 0 green 0 dwelltime 0 days 90

Watchlog COUNTER 1 1 green 0 dwelltime 0 days 90

Watchlog Counter 2 0 Green 0 Dwelltime 0 Days 90, the number of events in user history

Watchlog CLUSTER COUNTER 1 8 green 0 dwelltime 0 days 90

Watchlog CLUSTER COUNTER 3 8 green 0 dwelltime 0 days 90

Watchlog CLUSTER COUNTER 9 8 green 0 dwelltime 0 days 90

Watchlog CLUSTER COUNTER 9 10 green 0 dwelltime 0 days 90

Watchlog CLUSTER COUNTER 2 0 green 0 dwelltime 30 days 2

Watchlog CLUSTER COUNTER 1 0 green 0 dwelltime 30 days 14

Watchlog COUNTER 1 0 green 0 dwelltime 30 days 30

Watchlog COUNTER 1 1 green 0 dwelltime 30 days 30

Watchlog COUNTER 1 1 green 0 dwelltime 30 days 60

Watchlog Counter 2 0 Green 0 Dwelltime 30 Days 60, the number of events in the history of user

Watchlog COUNTER 1 1 green 0 dwelltime 30 days 90

Watchlog Counter 2 0 Green 0 Dwelltime 30 Days 90, the number of events in the history of user

Watchlog CLUSTER COUNTER 2 0 green 0 dwelltime 60 days 2

Watchlog CLUSTER COUNTER 3 0 green 0 dwelltime 60 days 14

Watchlog COUNTER 1 1 green 0 dwelltime 60 days 30

Watchlog COUNTER 1 1 green 0 dwelltime 60 days 60

Watchlog COUNTER 1 1 green 0 dwelltime 60 days 90

Watchlog Counter 2 0 Green 0 Dwelltime 60 Days 90, the number of events in the history of user

Watchlog CLUSTER COUNTER 4 10 green 0 dwelltime 60 days 90

Watchlog CLUSTER COUNTER 7 10 green 0 dwelltime 60 days 90

Watchlog CLUSTER COUNTER 9 8 green 0 dwelltime 60 days 90

Watchlog CLUSTER COUNTER 9 10 green 0 dwelltime 60 days 90

Watchlog COUNTER 1 1 green 0 dwelltime 120 days 30

Watchlog COUNTER 1 1 green 0 dwelltime 120 days 60

Watchlog CLUSTER 1 1 green 0 dwelltime 120 days 90

Watchlog CLUSTER 1 6 green 0 dwelltime 120 days 90

Watchlog CLUSTER 2 4 green 0 dwelltime 120 days 90

Watchlog CLUSTER 4 0 green 0 dwelltime 120 days 90

Watchlog COUNTER 1 0 green 0 dwelltime 120 days 90

Watchlog COUNTER 1 1 green 0 dwelltime 120 days 90

Watchlog Counter 2 0 Green 1 Dwelltime 0 Days 2, the number of events in user history

Watchlog Counter 2 0 Green 1 Dwelltime 0 Days 7, the number of events in the history of user

Watchlog COUNTER 2 1 green 1 dwelltime 0 days 7

Watchlog CLUSTER COUNTER 0 0 green 1 dwelltime 0 days 7

Watchlog Counter 2 0 Green 1 Dwelltime 0 Days 14, the number of events in user history

Watchlog COUNTER 2 1 green 1 dwelltime 0 days 14

Watchlog Counter 2 0 Green 1 Dwelltime 0 Days 30, the number of events in the history of user

Watchlog COUNTER 2 1 green 1 dwelltime 0 days 30

Watchlog CLUSTER COUNTER 0 0 green 1 dwelltime 0 days 30

Watchlog CLUSTER COUNTER 1 0 green 1 dwelltime 0 days 30

Watchlog Counter 2 0 Green 1 Dwelltime 0 Days 60, the number of events in the history of user

Watchlog CLUSTER 0 6 green 1 dwelltime 0 days 90

Watchlog CLUSTER 1 6 green 1 dwelltime 0 days 90

Watchlog CLUSTER 10 1 green 1 dwelltime 0 days 90

Watchlog Counter 2 0 Green 1 Dwelltime 0 Days 90, the number of events in user history

Watchlog CLUSTER COUNTER 9 8 green 1 dwelltime 0 days 90

Watchlog Counter 2 0 Green 1 Dwelltime 30 Days 60, the number of events in the history of user

Watchlog Counter 2 0 Green 1 Dwelltime 30 Days 90, the number of events in user history

Watchlog Counter 2 0 Green 1 Dwelltime 60 Days 14, the number of events in the history of user

Watchlog Counter 2 0 Green 1 Dwelltime 60 Days 30, the number of events in the history of user

Watchlog Counter 2 0 Green 1 Dwelltime 60 Days 60, the number of events in the history of user

Watchlog Counter 2 0 Green 1 Dwelltime 60 Days 90, the number of events in the history of user

Watchlog Counter 2 0 Green 1 Dwelltime 120 Days 2, the number of events in user history

Watchlog COUNTER 2 1 green 1 dwelltime 120 days 2

Watchlog CLUSTER COUNTER 0 0 green 1 dwelltime 120 days 2

Watchlog Counter 2 0 Green 1 Dwelltime 120 Days 7, the number of events in the history of user

Watchlog Counter 2 0 Green 1 Dwelltime 120 Days 14, the number of events in the history of user

Watchlog COUNTER 2 1 green 1 dwelltime 120 days 14

Watchlog Counter 2 0 Green 1 Dwelltime 120 Days 30, the number of events in the history of user

Watchlog COUNTER 2 1 green 1 dwelltime 120 days 30

Watchlog Counter 2 0 Green 1 Dwelltime 120 Days 60, the number of events in the history of user

Watchlog COUNTER 2 1 green 1 dwelltime 120 days 60

Watchlog CLUSTER 0 1 green 1 dwelltime 120 days 90

Watchlog CLUSTER 1 6 green 1 dwelltime 120 days 90

Watchlog CLUSTER 9 1 green 1 dwelltime 120 days 90

Watchlog CLUSTER 10 1 green 1 dwelltime 120 days 90

Watchlog COUNTER 2 0 green 1 dwelltime 120 days 90

Watchlog COUNTER 2 1 green 1 dwelltime 120 days 90

Spylog Counter 2 0 Green 0 Dwelltime 0 Days 2, number of events in the history of user

Spylog COUNTER 1 1 green 0 dwelltime 0 days 7

Spylog COUNTER 1 0 green 0 dwelltime 0 days 14

Spylog COUNTER 1 1 green 0 dwelltime 0 days 14

Spylog Counter 2 0 Green 0 Dwelltime 0 Days 14, the number of events in the history of user

Spylog COUNTER 1 0 green 0 dwelltime 0 days 30

Spylog COUNTER 1 1 green 0 dwelltime 0 days 30

Spylog COUNTER 1 0 green 0 dwelltime 0 days 60

Spylog COUNTER 1 1 green 0 dwelltime 0 days 60

Spylog CLUSTER 1 1 green 0 dwelltime 0 days 90

Spylog CLUSTER 1 6 green 0 dwelltime 0 days 90. Distance to the closest cluster in user history clustering divided by its weight

Spylog CLUSTER 1 7 green 0 dwelltime 0 days 90

Spylog COUNTER 1 0 green 0 dwelltime 0 days 90

Spylog COUNTER 1 1 green 0 dwelltime 0 days 90

Spylog Counter 2 0 Green 0 Dwelltime 0 Days 90, the number of events in the history of user

Spylog CLUSTER COUNTER 0 0 green 0 dwelltime 30 days 2

Spylog CLUSTER COUNTER 2 0 green 0 dwelltime 30 days 2

Spylog COUNTER 1 1 green 0 dwelltime 30 days 14

Spylog CLUSTER COUNTER 1 0 green 0 dwelltime 30 days 14

Spylog COUNTER 1 1 green 0 dwelltime 30 days 30

Spylog COUNTER 1 1 green 0 dwelltime 30 days 60

Spylog COUNTER 1 1 green 0 dwelltime 30 days 90

Spylog CLUSTER COUNTER 2 0 green 0 dwelltime 60 days 2

Spylog CLUSTER COUNTER 3 0 green 0 dwelltime 60 days 14

Spylog COUNTER 1 1 green 0 dwelltime 60 days 30

Spylog CLUSTER COUNTER 9 8 green 0 dwelltime 60 days 30

Spylog COUNTER 1 1 green 0 dwelltime 60 days 60

Spylog CLUSTER COUNTER 4 0 green 0 dwelltime 60 days 60

Spylog COUNTER 1 1 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 1 8 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 3 8 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 3 10 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 4 8 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 4 10 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 6 8 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 6 10 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 7 10 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 8 8 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 9 8 green 0 dwelltime 60 days 90

Spylog CLUSTER COUNTER 9 10 green 0 dwelltime 60 days 90

Spylog COUNTER 1 1 green 0 dwelltime 120 days 30

Spylog COUNTER 1 1 green 0 dwelltime 120 days 60

Spylog CLUSTER 1 1 green 0 dwelltime 120 days 90

Spylog CLUSTER 1 6 green 0 dwelltime 120 days 90

Spylog CLUSTER 2 4 green 0 dwelltime 120 days 90

Spylog COUNTER 1 1 green 0 dwelltime 120 days 90

Spylog Counter 2 0 Green 0 Dwelltime 120 Days 90, the number of events in the history of user

Spylog CLUSTER COUNTER 0 0 green 0 dwelltime 120 days 90

Spylog Counter 2 0 Green 1 Dwelltime 0 Days 7, the number of events in the history of user

Spylog CLUSTER COUNTER 0 0 green 1 dwelltime 0 days 7

Spylog COUNTER 1 0 green 1 dwelltime 0 days 30

Spylog Counter 2 0 Green 1 Dwelltime 0 Days 30, the number of events in the history of user

Spylog CLUSTER COUNTER 1 0 green 1 dwelltime 0 days 30

Spylog Counter 2 0 Green 1 Dwelltime 0 Days 60, the number of events in the history of user

Spylog COUNTER 2 1 green 1 dwelltime 0 days 60

Spylog CLUSTER 0 1 green 1 dwelltime 0 days 90

Spylog CLUSTER 0 2 green 1 dwelltime 0 days 90

Spylog CLUSTER 0 6 green 1 dwelltime 0 days 90

Spylog CLUSTER 1 1 green 1 dwelltime 0 days 90

Spylog CLUSTER 1 6 green 1 dwelltime 0 days 90

Spylog CLUSTER 1 7 green 1 dwelltime 0 days 90

Spylog COUNTER 1 0 green 1 dwelltime 0 days 90

Spylog COUNTER 1 1 green 1 dwelltime 0 days 90

Spylog Counter 2 0 Green 1 Dwelltime 0 Days 90, the number of events in the history of user

Spylog COUNTER 2 1 green 1 dwelltime 0 days 90

Spylog COUNTER 1 1 green 1 dwelltime 30 days 90

Spylog Counter 2 0 Green 1 Dwelltime 30 Days 90, the number of events in the history of user

Spylog CLUSTER COUNTER 9 8 green 1 dwelltime 30 days 90

Spylog CLUSTER COUNTER 9 0 green 1 dwelltime 60 days 7

Spylog COUNTER 1 1 green 1 dwelltime 60 days 30

Spylog Counter 2 0 Green 1 Dwelltime 60 Days 30, the number of events in the history of user

Spylog COUNTER 1 1 green 1 dwelltime 60 days 60

Spylog Counter 2 0 Green 1 Dwelltime 60 Days 60, the number of events in the history of user

Spylog COUNTER 1 1 green 1 dwelltime 60 days 90

Spylog Counter 2 0 Green 1 Dwelltime 60 Days 90, the number of events in the history of user

Spylog Counter 2 0 Green 1 Dwelltime 120 Days 2, number of events in the history of user

Spylog COUNTER 2 1 green 1 dwelltime 120 days 2

Spylog CLUSTER COUNTER 0 0 green 1 dwelltime 120 days 2

Spylog Counter 2 0 Green 1 Dwelltime 120 Days 7, the number of events in the history of user

Spylog COUNTER 2 1 green 1 dwelltime 120 days 7

Spylog Counter 2 0 Green 1 Dwelltime 120 Days 14, the number of events in the history of user

Spylog COUNTER 1 1 green 1 dwelltime 120 days 30

Spylog Counter 2 0 Green 1 Dwelltime 120 Days 30, the number of events in the history of user

Spylog COUNTER 2 1 green 1 dwelltime 120 days 30

Spylog Counter 2 0 Green 1 Dwelltime 120 Days 60, the number of events in the history of user

Spylog COUNTER 2 1 green 1 dwelltime 120 days 60

Spylog CLUSTER 0 1 green 1 dwelltime 120 days 90

Spylog CLUSTER 1 1 green 1 dwelltime 120 days 90

Spylog CLUSTER 1 6 green 1 dwelltime 120 days 90

Spylog COUNTER 1 1 green 1 dwelltime 120 days 90

Spylog Counter 2 0 Green 1 Dwelltime 120 Days 90, the number of events in the history of the user

Spylog COUNTER 2 1 green 1 dwelltime 120 days 90

Yabslog CLICKS COUNTER 0 1 days 7

Yabslog CLICKS COUNTER 1 0 days 7

Yabslog CLICKS COUNTER 1 1 days 7

Yabslog CLICKS COUNTER 2 0 days 7

Yabslog CLICKS COUNTER 2 1 days 7

Yabslog CLICKS COUNTER 0 0 days 14

Yabslog CLICKS COUNTER 0 1 days 14

Yabslog CLICKS COUNTER 1 0 days 14

Yabslog CLICKS COUNTER 1 1 days 14

Yabslog CLICKS COUNTER 2 0 days 14

Yabslog CLICKS COUNTER 2 1 days 14

Yabslog CLICKS COUNTER 0 0 days 30

Yabslog CLICKS COUNTER 1 0 days 30

Yabslog CLICKS COUNTER 2 0 days 30

Yabslog CLICKS COUNTER 2 1 days 30

Yabslog CLICKS COUNTER 0 0 days 60

Yabslog CLICKS COUNTER 1 0 days 60

Yabslog CLICKS COUNTER 2 0 days 60

Yabslog CLICKS COUNTER 2 1 days 60

Yabslog CLICKS CLUSTER 0 0 days 90

Yabslog CLICKS CLUSTER 0 1 days 90

Yabslog CLICKS CLUSTER 0 2 days 90

Yabslog CLICKS CLUSTER 1 0 days 90

Yabslog CLICKS CLUSTER 1 1 days 90

Yabslog CLICKS CLUSTER 1 2 days 90

Yabslog CLICKS CLUSTER 1 6 days 90

Yabslog CLICKS COUNTER 0 0 days 90

Yabslog CLICKS COUNTER 1 0 days 90

Yabslog CLICKS COUNTER 1 1 days 90

Yabslog CLICKS COUNTER 2 0 days 90

Yabslog CLICKS COUNTER 2 1 days 90

Yabslog SHOWS COUNTER 0 1 days 7

Yabslog SHOWS COUNTER 1 0 days 7

Yabslog SHOWS COUNTER 1 1 days 7

Yabslog SHOWS COUNTER 2 0 days 7

Yabslog SHOWS COUNTER 2 1 days 7

Yabslog SHOWS COUNTER 0 0 days 14

Yabslog SHOWS COUNTER 0 1 days 14

Yabslog SHOWS COUNTER 1 0 days 14

Yabslog SHOWS COUNTER 1 1 days 14

Yabslog SHOWS COUNTER 2 0 days 14

Yabslog SHOWS COUNTER 2 1 days 14

Yabslog SHOWS COUNTER 0 0 days 30

Yabslog SHOWS COUNTER 1 0 days 30

Yabslog SHOWS COUNTER 2 0 days 30

Yabslog SHOWS COUNTER 2 1 days 30

Yabslog SHOWS COUNTER 0 0 days 60

Yabslog SHOWS COUNTER 1 0 days 60

Yabslog SHOWS COUNTER 2 0 days 60

Yabslog SHOWS COUNTER 2 1 days 60

Yabslog SHOWS CLUSTER 0 0 days 90

Yabslog SHOWS CLUSTER 0 1 days 90

Yabslog SHOWS CLUSTER 0 2 days 90

Yabslog SHOWS CLUSTER 1 0 days 90

Yabslog SHOWS CLUSTER 1 1 days 90

Yabslog SHOWS CLUSTER 1 2 days 90

Yabslog SHOWS CLUSTER 1 6 days 90

Yabslog SHOWS COUNTER 0 0 days 90

Yabslog SHOWS COUNTER 1 0 days 90

Yabslog SHOWS COUNTER 1 1 days 90

Yabslog SHOWS COUNTER 2 0 days 90

Yabslog SHOWS COUNTER 2 1 days 90

Max cosine similarity between document and user history with clicks dwelltime > 30sec, by realtime user_history

Max cosine similarity between document and user history with clicks dwelltime > 60sec, by realtime user_history

Max cosine similarity between document and user history with clicks dwelltime > 120sec, by realtime user_history

Max cosine similarity between document and user history with clicks dwelltime > 180sec, by realtime user_history

Max cosine similarity between document and user history with clicks dwelltime > 360sec, by realtime user_history

Max cosine similarity between document and user history with clicks dwelltime <= 30sec, by realtime user_history

Max cosine similarity between document and user history with clicks dwelltime <= 60sec, by realtime user_history

Max cosine similarity between document and user history with clicks dwelltime <= 120sec, by realtime user_history

Max cosine similarity between document and user history with clicks dwelltime <= 180sec, by realtime user_history

Max cosine similarity between document and user history with clicks dwelltime <= 360sec, by realtime user_history

Avg by top-5 maximum cosine similarity between document and user history with clicks dwelltime > 30sec, by realtime user_history

Avg by top-5 maximum cosine similarity between document and user history with clicks dwelltime > 60sec, by realtime user_history

Avg by top-5 maximum cosine similarity between document and user history with clicks dwelltime > 120sec, by realtime user_history

Avg by top-5 maximum cosine similarity between document and user history with clicks dwelltime > 180sec, by realtime user_history

Avg by top-5 maximum cosine similarity between document and user history with clicks dwelltime > 360sec, by realtime user_history

Avg by top-10 maximum cosine similarity between document and user history with clicks dwelltime > 30sec, by realtime user_history

Avg by top-10 maximum cosine similarity between document and user history with clicks dwelltime > 60sec, by realtime user_history

Avg by top-10 maximum cosine similarity between document and user history with clicks dwelltime > 120sec, by realtime user_history

Avg by top-10 maximum cosine similarity between document and user history with clicks dwelltime > 180sec, by realtime user_history

Avg by top-10 maximum cosine similarity between document and user history with clicks dwelltime > 360sec, by realtime user_history

Avg by top-15 maximum cosine similarity between document and user history with clicks dwelltime > 30sec, by realtime user_history

Avg by top-15 maximum cosine similarity between document and user history with clicks dwelltime > 60sec, by realtime user_history

Avg by top-15 maximum cosine similarity between document and user history with clicks dwelltime > 120sec, by realtime user_history

Avg by top-15 maximum cosine similarity between document and user history with clicks dwelltime > 180sec, by realtime user_history

Avg by top-15 maximum cosine similarity between document and user history with clicks dwelltime > 360sec, by realtime user_history

HostTopicShows to HostShows fraction by realtime user_profiles

HostTopicClicks to HostClicks fraction by realtime user_profiles

L2 version DOPPURLCTRLOG5DECAY30 factor

L2 factor similar to Doppurlosctrlog5Decay30 only with fixed OS on iOS