Slice: web_meta_pers
(161 ranking factors)
Factors |
---|
FadingEmbLogDwelltimeBigramsDoc01daysDwt120Less
web_meta_pers: 0
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime less than 120sec)
|
FadingEmbLogDwelltimeBigramsDoc01daysDwt120More
web_meta_pers: 1
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 120sec)
|
FadingEmbLogDwelltimeBigramsDoc05daysDwt120Less
web_meta_pers: 2
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.5days, dwelltime less than 120sec)
|
FadingEmbLogDwelltimeBigramsDoc05daysDwt120More
web_meta_pers: 3
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.5days, dwelltime more than 120sec)
|
FadingEmbLogDwelltimeBigramsDoc3daysDwt120Less
web_meta_pers: 4
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=3days, dwelltime less than 120sec)
|
FadingEmbLogDwelltimeBigramsDoc3daysDwt120More
web_meta_pers: 5
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=3days, dwelltime more than 120sec)
|
DifferentTrigramsCountPrevQCurQRealtime
web_meta_pers: 6
Saturated number of different trigrams for current and previous query by realtime user_actions
|
DifferentWordsCountPrevQCurQRealtime
web_meta_pers: 7
Saturated number of different words in current and previous query by realtime user_actions
|
CurQSessionMatchingTrigramsRealtime
web_meta_pers: 8
Sat(MatchingTrigramsAmount(current request, user requests)), realtime user_actions
|
CurQSessionBm25FixedRealtime
web_meta_pers: 9
Sat(BM25(current query, user requests)) by realtime user_actions
|
FadingEmbLogDwelltimeBigramsDocXQuery01daysDwt120Less
web_meta_pers: 10
Cosine similarity between query embedding and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime less than 120sec)
|
FadingEmbLogDwelltimeBigramsDocXQuery01daysDwt120More
web_meta_pers: 11
Cosine similarity between query embedding and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 120sec)
|
FadingEmbLogDwelltimeBigramsDocXQuery05daysDwt120Less
web_meta_pers: 12
Cosine similarity between query embedding and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.5days, dwelltime less than 120sec)
|
FadingEmbLogDwelltimeBigramsDocXQuery05daysDwt120More
web_meta_pers: 13
Cosine similarity between query embedding and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.5days, dwelltime more than 120sec)
|
FadingEmbLogDwelltimeBigramsDocXQuery3daysDwt120Less
web_meta_pers: 14
Cosine similarity between query embedding and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=3days, dwelltime less than 120sec)
|
FadingEmbLogDwelltimeBigramsDocXQuery3daysDwt120More
web_meta_pers: 15
Cosine similarity between query embedding and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=3days, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120LessTopavg1
web_meta_pers: 16
Top1 weighted average cosine similarity between document and clustered embedding of documents from user_history (model=LogDwellTimeBigrams, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120MoreTopavg1
web_meta_pers: 17
Top1 weighted average cosine similarity between document and clustered embedding of documents from user_history (model=LogDwellTimeBigrams, dwelltime less than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120LessTopavg2
web_meta_pers: 18
Top2 weighted average cosine similarity between document and clustered embedding of documents from user_history (model=LogDwellTimeBigrams, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120MoreTopavg2
web_meta_pers: 19
Top2 weighted average cosine similarity between document and clustered embedding of documents from user_history (model=LogDwellTimeBigrams, dwelltime less than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120LessCounter30
web_meta_pers: 20
cnt / (1 + cnt), cnt = sum of weights where cosine between document and clustered embedding of documents from user_history > 0.30 (model=LogDwellTimeBigrams, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120MoreCounter30
web_meta_pers: 21
cnt / (1 + cnt), cnt = sum of weights where cosine between document and clustered embedding of documents from user_history > 0.30 (model=LogDwellTimeBigrams, dwelltime less than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120LessCounter60
web_meta_pers: 22
cnt / (1 + cnt), cnt = sum of weights where cosine between document and clustered embedding of documents from user_history > 0.60 (model=LogDwellTimeBigrams, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120MoreCounter60
web_meta_pers: 23
cnt / (1 + cnt), cnt = sum of weights where cosine between document and clustered embedding of documents from user_history > 0.60 (model=LogDwellTimeBigrams, dwelltime less than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120LessCounter90
web_meta_pers: 24
cnt / (1 + cnt), cnt = sum of weights where cosine between document and clustered embedding of documents from user_history > 0.90 (model=LogDwellTimeBigrams, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocDwt120MoreCounter90
web_meta_pers: 25
cnt / (1 + cnt), cnt = sum of weights where cosine between document and clustered embedding of documents from user_history > 0.90 (model=LogDwellTimeBigrams, dwelltime less than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocXQueryDwt120LessTopavg1
web_meta_pers: 26
Top1 weighted average cosine similarity between query embedding and clustered embedding of documents from user_history (model=LogDwellTimeBigrams, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocXQueryDwt120MoreTopavg1
web_meta_pers: 27
Top1 weighted average cosine similarity between query embedding and clustered embedding of documents from user_history (model=LogDwellTimeBigrams, dwelltime less than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocXQueryDwt120LessTopavg2
web_meta_pers: 28
Top2 weighted average cosine similarity between query embedding and clustered embedding of documents from user_history (model=LogDwellTimeBigrams, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocXQueryDwt120MoreTopavg2
web_meta_pers: 29
Top2 weighted average cosine similarity between query embedding and clustered embedding of documents from user_history (model=LogDwellTimeBigrams, dwelltime less than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocXQueryDwt120LessCounter30
web_meta_pers: 30
cnt / (1 + cnt), cnt = sum of weights where cosine between query embedding and clustered embedding of documents from user_history > 0.30 (model=LogDwellTimeBigrams, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocXQueryDwt120MoreCounter30
web_meta_pers: 31
cnt / (1 + cnt), cnt = sum of weights where cosine between query embedding and clustered embedding of documents from user_history > 0.30 (model=LogDwellTimeBigrams, dwelltime less than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocXQueryDwt120LessCounter60
web_meta_pers: 32
cnt / (1 + cnt), cnt = sum of weights where cosine between query embedding and clustered embedding of documents from user_history > 0.60 (model=LogDwellTimeBigrams, dwelltime more than 120sec)
|
ClusteredEmbLogDwelltimeBigramsDocXQueryDwt120MoreCounter60
web_meta_pers: 33
cnt / (1 + cnt), cnt = sum of weights where cosine between query embedding and clustered embedding of documents from user_history > 0.60 (model=LogDwellTimeBigrams, dwelltime less than 120sec)
|
Removed34
web_meta_pers: 34
|
Removed35
web_meta_pers: 35
|
QIsSameAsPrevQRealtime
web_meta_pers: 36
Normalized query equals to previous one in session by realtime user_actions
|
FadingEmbLogDwelltimeBigramsDeltaTimestamp01daysDwt120Less
web_meta_pers: 37
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime less than 120sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestamp01daysDwt120More
web_meta_pers: 38
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 120sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestamp05daysDwt120Less
web_meta_pers: 39
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.5days, dwelltime less than 120sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestamp05daysDwt120More
web_meta_pers: 40
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.5days, dwelltime more than 120sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestamp3daysDwt120Less
web_meta_pers: 41
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=3days, dwelltime less than 120sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestamp3daysDwt120More
web_meta_pers: 42
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=3days, dwelltime more than 120sec)
|
TimeBetweenPrevAndCurQ
web_meta_pers: 43
Saturated time between current and previous query
|
LogDwelltimeUserAllClicksDwt0allXQueryEmbMaxScoreXWeight
web_meta_pers: 44
DotProducts = (all click embeddings from user_history) * QueryEmb, Take top1 weighted DotProduct
|
LogDwelltimeUserAllClicksDwt0allXDocEmbMaxScoreXWeight
web_meta_pers: 45
DotProducts = (all click embeddings from user_history) * DocEmb, Take top1 weighted DotProduct
|
LogDwelltimeUserAllClicksDwt60lessXDocEmbMaxScoreXWeight
web_meta_pers: 46
DotProducts = (all click embeddings from user_history where dwelltime < 60) * DocEmb, Take top1 weighted DotProduct
|
LogDwelltimeUserAllClicksDwt60lessXDocEmbScoreThreshold50pCount
web_meta_pers: 47
DotProducts = (all click embeddings from user_history where dwelltime < 60) * DocEmb, Take DotProducts > 0.50, f = count / count + 10
|
LogDwelltimeUserAllClicksDwt60lessXDocEmbMinscore
web_meta_pers: 48
DotProducts = (all click embeddings from user_history where dwelltime < 60) * DocEmb, min DotProducts
|
LogDwelltimeUserAllClicksDwt60moreXDocEmbAvgtop2ScoreXWeight
web_meta_pers: 49
DotProducts = (all click embeddings from user_history where dwelltime >= 60) * DocEmb, Take average of top2 weighted DotProducts
|
LogDwelltimeUserAllClicksDwt60moreXDocEmbAvgtop4ScoreXWeight
web_meta_pers: 50
DotProducts = (all click embeddings from user_history where dwelltime >= 60) * DocEmb, Take average of top4 weighted DotProducts
|
LogDwelltimeUserAllClicksDwt90moreXDocEmbAvgtop2ScoreXWeight
web_meta_pers: 51
DotProducts = (all click embeddings from user_history where dwelltime >= 90) * DocEmb, Take average of top2 weighted DotProducts
|
LogDwelltimeUserAllClicksDwt90moreXDocEmbScoreThreshold40pCount
web_meta_pers: 52
DotProducts = (all click embeddings from user_history where dwelltime >= 90) * DocEmb, Take DotProducts > 0.40, f = count / count + 10
|
LogDwelltimeUserAllClicksDwt90moreXDocEmbMintop40pScore
web_meta_pers: 53
DotProducts = (all click embeddings from user_history where dwelltime >= 90) * DocEmb, sort descending, f = DotProducts[0.4 * len(DotProducts)]
|
LogDwelltimeUserAllClicksDwt180moreXDocEmbAvgtop4ScoreXWeight
web_meta_pers: 54
DotProducts = (all click embeddings from user_history where dwelltime >= 180) * DocEmb, Take average of top4 weighted DotProducts
|
LogDwelltimeUserAllClicksDwt210moreXDocEmbMintop10pScore
web_meta_pers: 55
DotProducts = (all click embeddings from user_history where dwelltime >= 210) * DocEmb, sort descending, f = DotProducts[0.1 * len(DotProducts)]
|
LogDwelltimeUserAllClicksDwt450moreXDocEmbScoreThreshold100pRelcount
web_meta_pers: 56
DotProducts = (all click embeddings from user_history where dwelltime >= 450) * DocEmb, Take DotProducts > 0.10, f = 2 * count / (count + len(DotProducts))
|
LogDwelltimeUserLong120ClicksDwt600moreXQueryEmbMintop20pScore
web_meta_pers: 57
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 600) * QueryEmb, sort descending, f = DotProducts[0.2 * len(DotProducts)]
|
LogDwelltimeUserLong120ClicksDwt30moreXDocEmbMaxscore
web_meta_pers: 58
DotProducts = (longer 120s click embeddings from user_history) * DocEmb, max DotProducts
|
LogDwelltimeUserLong120ClicksDwt180lessXDocEmbAvgtop30pScoreXWeight
web_meta_pers: 59
DotProducts = (longer 120s click embeddings from user_history where dwelltime < 180) * DocEmb, Take average of top(0.30 * len(DotProducts)) weighted DotProducts
|
LogDwelltimeUserLong120ClicksDwt180lessXDocEmbMintop90pScore
web_meta_pers: 60
DotProducts = (longer 120s click embeddings from user_history where dwelltime < 180) * DocEmb, sort descending, f = DotProducts[0.9 * len(DotProducts)]
|
LogDwelltimeUserLong120ClicksDwt180moreXDocEmbMaxScoreXWeight
web_meta_pers: 61
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 180) * DocEmb, Take top1 weighted DotProduct
|
LogDwelltimeUserLong120ClicksDwt180moreXDocEmbAvgtop2ScoreXWeight
web_meta_pers: 62
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 180) * DocEmb, Take average of top2 weighted DotProducts
|
LogDwelltimeUserLong120ClicksDwt360moreXDocEmbMaxScoreXWeight
web_meta_pers: 63
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 360) * DocEmb, Take top1 weighted DotProduct
|
LogDwelltimeUserLong120ClicksDwt360moreXDocEmbAvgtop10pScoreXWeight
web_meta_pers: 64
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 360) * DocEmb, Take average of top(0.10 * len(DotProducts)) weighted DotProducts
|
LogDwelltimeUserLong120ClicksDwt360moreXDocEmbAvgtop2ScoreXWeight
web_meta_pers: 65
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 360) * DocEmb, Take average of top2 weighted DotProducts
|
LogDwelltimeUserLong120ClicksDwt360moreXDocEmbMintop20pScore
web_meta_pers: 66
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 360) * DocEmb, sort descending, f = DotProducts[0.2 * len(DotProducts)]
|
LogDwelltimeUserLong120ClicksDwt600lessXDocEmbMaxScoreXWeight
web_meta_pers: 67
DotProducts = (longer 120s click embeddings from user_history where dwelltime < 600) * DocEmb, Take top1 weighted DotProduct
|
LogDwelltimeUserLong120ClicksDwt600lessXDocEmbAvgtop2ScoreXWeight
web_meta_pers: 68
DotProducts = (longer 120s click embeddings from user_history where dwelltime < 600) * DocEmb, Take average of top2 weighted DotProducts
|
LogDwelltimeUserLong120ClicksDwt600lessXDocEmbScoreThreshold50pCount
web_meta_pers: 69
DotProducts = (longer 120s click embeddings from user_history where dwelltime < 600) * DocEmb, Take DotProducts > 0.50, f = count / count + 10
|
LogDwelltimeUserLong120ClicksDwt600moreXDocEmbAvgtop2ScoreXWeight
web_meta_pers: 70
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 600) * DocEmb, Take average of top2 weighted DotProducts
|
LogDwelltimeUserLong120ClicksDwt600moreXDocEmbScoreThreshold40pSaturatedweightsum
web_meta_pers: 71
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 600) * DocEmb, Take DotProducts > 0.40, f = weightSum / (weightSum + 1)
|
LogDwelltimeUserLong120ClicksDwt600moreXDocEmbScoreThreshold100pRelcount
web_meta_pers: 72
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 600) * DocEmb, Take DotProducts > 0.10, f = 2 * count / (count + len(DotProducts))
|
LogDwelltimeUserLong120ClicksDwt600moreXDocEmbMaxscore
web_meta_pers: 73
DotProducts = (longer 120s click embeddings from user_history where dwelltime >= 600) * DocEmb, max DotProducts
|
FadingEmbLogDwelltimeBigramsDocXQueryDays01Dwt30Less
web_meta_pers: 74
Cosine similarity between query embedding and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime less than 30sec)
|
FadingEmbLogDwelltimeBigramsDocXQueryDays01Dwt30More
web_meta_pers: 75
Cosine similarity between query embedding and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 30sec)
|
FadingEmbLogDwelltimeBigramsDocXQueryDays01Dwt300Less
web_meta_pers: 76
Cosine similarity between query embedding and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime less than 300sec)
|
FadingEmbLogDwelltimeBigramsDocDays01Dwt30More
web_meta_pers: 77
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 30sec)
|
FadingEmbLogDwelltimeBigramsDocDays01Dwt300More
web_meta_pers: 78
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 300sec)
|
FadingEmbLogDwelltimeBigramsDocDays01Dwt600More
web_meta_pers: 79
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 600sec)
|
FadingEmbLogDwelltimeBigramsDocDays12Dwt90More
web_meta_pers: 80
Cosine similarity between document and fading embedding of documents from RTMR user_history (model=LogDwellTimeBigrams, fadingCoef=12days, dwelltime more than 90sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestampDays01Dwt30More
web_meta_pers: 81
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 30sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestampDays01Dwt90Less
web_meta_pers: 82
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime less than 90sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestampDays01Dwt300More
web_meta_pers: 83
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 300sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestampDays02Dwt600Less
web_meta_pers: 84
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.2days, dwelltime less than 600sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestampDays03Dwt30More
web_meta_pers: 85
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.3days, dwelltime more than 30sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestampDays03Dwt600More
web_meta_pers: 86
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.3days, dwelltime more than 600sec)
|
FadingEmbLogDwelltimeBigramsDeltaTimestampDays300Dwt30Less
web_meta_pers: 87
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=300days, dwelltime less than 120sec DWT30)
|
ClustEmbLogDtBigramsDocXQueryDwt120LessWeights5LessMinscore
web_meta_pers: 88
Take clustered embeddings (short clicks, centroids with weights less than 5), Calc dot products with query embedding, f = Min(DotProducts)
|
ClustEmbLogDtBigramsDocDwt120LessWeights0AllScoreThreshold95pSatweightsum
web_meta_pers: 89
Take clustered embeddings (short clicks), Calc dot products with doc embedding, Take dot product more than 0.95, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsDocXQueryDwt120MoreWeights5LessMintop10pScore
web_meta_pers: 90
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with query embedding, sort descending, f = DotProducts[0.10 * DotProduct.size()]
|
ClustEmbLogDtBigramsDocXQueryDwt120MoreWeights5LessMintop90pScore
web_meta_pers: 91
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with query embedding, sort descending, f = DotProducts[0.90 * DotProduct.size()]
|
ClustEmbLogDtBigramsDocXQueryDwt120MoreWeights5LessMinscore
web_meta_pers: 92
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with query embedding, f = Min(DotProducts)
|
ClustEmbLogDtBigramsDocXQueryDwt120MoreWeights5LessScoreThreshold30pSatweightsum
web_meta_pers: 93
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with query embedding, Take dot product more than 0.30, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsDocXQueryDwt120MoreWeights5LessScoreThreshold40pCount
web_meta_pers: 94
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with query embedding, Take dot product more than 0.40, f = count / (count + 10)
|
ClustEmbLogDtBigramsDocXQueryDwt120MoreWeights5LessScoreThreshold40pSatweightsum
web_meta_pers: 95
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with query embedding, Take dot product more than 0.40, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsDocXQueryDwt120MoreWeights10LessAvgtop5Scorexweight
web_meta_pers: 96
Take clustered embeddings (long clicks, centroids with weights less than 10), Calc dot products with query embedding, sort descending, take top5, f = AVG(DotProduct[i] * Weight[i])
|
ClustEmbLogDtBigramsDocDwt120MoreWeights0AllMaxscore
web_meta_pers: 97
Take clustered embeddings (long clicks), Calc dot products with doc embedding, f = Max(DotProduct)
|
ClustEmbLogDtBigramsDocDwt120MoreWeights0AllMaxScorexweight
web_meta_pers: 98
Take clustered embeddings (long clicks), Calc dot products with doc embedding, f = AVG(DotProduct[i] * Weight[i])
|
ClustEmbLogDtBigramsDocDwt120MoreWeights0AllScoreThreshold95pSatweightsum
web_meta_pers: 99
Take clustered embeddings (long clicks), Calc dot products with doc embedding, Take dot product more than 0.95, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsDocDwt120MoreWeights5LessMaxscore
web_meta_pers: 100
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with doc embedding, f = Max(DotProduct)
|
ClustEmbLogDtBigramsDocDwt120MoreWeights5LessMintop5pScore
web_meta_pers: 101
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with doc embedding, sort descending, f = DotProducts[0.05 * DotProduct.size()]
|
ClustEmbLogDtBigramsDocDwt120MoreWeights5LessMintop30pScore
web_meta_pers: 102
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with doc embedding, sort descending, f = DotProducts[0.30 * DotProduct.size()]
|
ClustEmbLogDtBigramsDocDwt120MoreWeights5LessMinscore
web_meta_pers: 103
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with doc embedding, f = Min(DotProducts)
|
ClustEmbLogDtBigramsDocDwt120MoreWeights5LessAvgtop5pScorexweight
web_meta_pers: 104
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with doc embedding, sort descending, take top5, f = AVG(DotProduct[i] * Weight[i])
|
ClustEmbLogDtBigramsDocDwt120MoreWeights5LessScoreThreshold30pSatweightsum
web_meta_pers: 105
Take clustered embeddings (long clicks, centroids with weights less than 5), Calc dot products with doc embedding, Take dot product more than 0.30, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsDocDwt120MoreWeights5MoreMintop10pScore
web_meta_pers: 106
Take clustered embeddings (long clicks, centroids with weights more than 5), Calc dot products with doc embedding, sort descending, f = DotProducts[0.10 * DotProduct.size()]
|
ClustEmbLogDtBigramsDocDwt120MoreWeights10LessMaxscore
web_meta_pers: 107
Take clustered embeddings (long clicks, centroids with weights less than 10), Calc dot products with doc embedding, f = Max(DotProduct)
|
ClustEmbLogDtBigramsDocDwt120MoreWeights10LessMintop10pScore
web_meta_pers: 108
Take clustered embeddings (long clicks, centroids with weights less than 10), Calc dot products with doc embedding, sort descending, f = DotProducts[0.10 * DotProduct.size()]
|
ClustEmbLogDtBigramsDocDwt120MoreWeights20LessMaxScorexweight
web_meta_pers: 109
Take clustered embeddings (long clicks, centroids with weights less than 20), Calc dot products with doc embedding, f = AVG(DotProduct[i] * Weight[i])
|
ClustEmbLogDtBigramsDocDwt120MoreWeights20LessScoreThreshold70pSatweightsum
web_meta_pers: 110
Take clustered embeddings (long clicks, centroids with weights less than 20), Calc dot products with doc embedding, Take dot product more than 0.70, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsDocDwt120MoreWeights30LessMaxscore
web_meta_pers: 111
Take clustered embeddings (long clicks, centroids with weights less than 30), Calc dot products with doc embedding, f = Max(DotProduct)
|
ClustEmbLogDtBigramsDocDwt120MoreWeights30LessAvgtop20pScorexweight
web_meta_pers: 112
Take clustered embeddings (long clicks, centroids with weights less than 30), Calc dot products with doc embedding, sort descending, take top20, f = AVG(DotProduct[i] * Weight[i])
|
CommonWordsCountPrevQCurQRealtime
web_meta_pers: 113
Saturated number of common words in current and previous query
|
FadingEmbLogDwelltimeBigramsQuery001days
web_meta_pers: 114
Cosine similarity between query embedding and fading embedding of queries from RTMR user_history, (model=LogDwellTimeBigrams, fadingCoef=0.01days)
|
FadingEmbLogDwelltimeBigramsQuery002days
web_meta_pers: 115
Cosine similarity between query embedding and fading embedding of queries from RTMR user_history, (model=LogDwellTimeBigrams, fadingCoef=0.02days)
|
FadingEmbLogDwelltimeBigramsQueryXDoc001days
web_meta_pers: 116
Cosine similarity between doc embedding and fading embedding of queries from RTMR user_history, (model=LogDwellTimeBigrams, fadingCoef=0.01days)
|
FadingEmbLogDwelltimeBigramsQueryDeltaTimestamp003days
web_meta_pers: 117
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.03days)
|
FadingEmbLogDwelltimeBigramsQueryDeltaTimestamp12days
web_meta_pers: 118
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=1.2days)
|
FadingEmbLogDwelltimeBigramsQueryDeltaTimestamp6days
web_meta_pers: 119
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=6days)
|
FadingEmbLogDwelltimeBigramsQueryDeltaTimestamp14days
web_meta_pers: 120
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=14days)
|
ClustEmbLogDtBigramsQueryAllWeightsAvgtop4ScoreXWeight
web_meta_pers: 121
Take clustered embeddings (query embeddings, all weights), Calc dot product with query embedding, Take top4, f = AVG(Score[i] * Weight[i])
|
ClustEmbLogDtBigramsQueryAllWeightsScoreThreshold75pSatweightsum
web_meta_pers: 122
Take clustered embeddings (query embeddings, all weights), Calc dot product with query embedding, Take dot product with score > 0.75, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsQueryWeights3LessMintop95pScore
web_meta_pers: 123
Take clustered embeddings (query embeddings, weights less than 3), Calc dot product with query embedding, Sort descending, f = DotProduct[0.95 * length(DotProducts)]
|
ClustEmbLogDtBigramsQueryWeights5LessScoreThreshold55pSatweightsum
web_meta_pers: 124
Take clustered embeddings (query embeddings, weights less than 5), Calc dot product with query embedding, Take dot product with score > 0.55, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsQueryWeights5LessMinscore
web_meta_pers: 125
Take clustered embeddings (query embeddings, weights less than 5), Calc dot product with query embedding, f = MIN(DotProducts)
|
ClustEmbLogDtBigramsQueryWeights10LessMaxscore
web_meta_pers: 126
Take clustered embeddings (query embeddings, weights less than 10), Calc dot product with query embedding, f = MAX(DotProducts)
|
ClustEmbLogDtBigramsQueryWeights15LessMaxScoreXWeight
web_meta_pers: 127
Take clustered embeddings (query embeddings, weights less than 15), Calc dot product with query embedding, f = MAX(Score[i] * Weights[i])
|
ClustEmbLogDtBigramsQueryWeights20LessScoreThreshold70pSatweightsum
web_meta_pers: 128
Take clustered embeddings (query embeddings, weights less than 20), Calc dot product with query embedding, Take dot product with score > 0.70, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsQueryAllWeightsMaxScoreXWeight
web_meta_pers: 129
Take clustered embeddings (query embeddings, all weights), Calc dot product with query embedding, f = MAX(Score[i] * Weights[i])
|
ClustEmbLogDtBigramsQueryXDocWeights3LessMintop5pScore
web_meta_pers: 130
Take clustered embeddings (query embeddings, weights less than 3), Calc dot product with doc embedding, Sort descending, f = DotProduct[0.05 * length(DotProducts)]
|
ClustEmbLogDtBigramsQueryXDocWeights3LessMinscore
web_meta_pers: 131
Take clustered embeddings (query embeddings, weights less than 3), Calc dot product with doc embedding, f = MIN(DotProducts)
|
ClustEmbLogDtBigramsQueryXDocWeights5LessMinscore
web_meta_pers: 132
Take clustered embeddings (query embeddings, weights less than 5), Calc dot product with doc embedding, f = MIN(DotProducts)
|
ClustEmbLogDtBigramsQueryXDocWeights15LessScoreThreshold45pSatweightsum
web_meta_pers: 133
Take clustered embeddings (query embeddings, weights less than 15), Calc dot product with doc embedding, Take dot product with score > 0.45, f = 1 / (1 + sum of weights)
|
ClustEmbLogDtBigramsQueryXDocAllWeightsMaxScoreXWeight
web_meta_pers: 134
Take clustered embeddings (query embeddings, all weights), Calc dot product with doc embedding, f = MAX(Score[i] * Weights[i])
|
ClustEmbLogDtBigramsQueryXDocAllWeightsScoreThreshold55pSatweightsum
web_meta_pers: 135
Take clustered embeddings (query embeddings, all weights), Calc dot product with doc embedding, Take dot product with score > 0.55, f = 1 / (1 + sum of weights)
|
LogDtBigramsUserLast10QueriesMaxScoreXWeight
web_meta_pers: 136
Take last 10 query embeddings, Calc dot product with query embedding, f = MAX(Score[i] * Weights[i])
|
LogDtBigramsUserLast10QueriesXDocMaxScoreXWeight
web_meta_pers: 137
Take last 10 query embeddings, Calc dot product with doc embedding, f = MAX(Score[i] * Weights[i])
|
LogDtBigramsUserLast20QueriesMaxScoreXWeight
web_meta_pers: 138
Take last 20 query embeddings, Calc dot product with query embedding, f = MAX(Score[i] * Weights[i])
|
LogDtBigramsUserLast20QueriesAvgtop3ScoreXWeight
web_meta_pers: 139
Take last 20 query embeddings, Calc dot product with query embedding, Take top3, f = AVG(Score[i] * Weight[i])
|
LogDtBigramsUserLast30QueriesMintop5pScore
web_meta_pers: 140
Take last 30 query embeddings, Calc dot product with query embedding, Sort descending, f = DotProduct[0.05 * length(DotProducts)]
|
LogDtBigramsUserLast40QueriesMaxScoreXWeight
web_meta_pers: 141
Take last 40 query embeddings, Calc dot product with query embedding, f = MAX(Score[i] * Weights[i])
|
LogDtBigramsUserLast50QueriesMaxscore
web_meta_pers: 142
Take last 50 query embeddings, Calc dot product with query embedding, f = MAX(DotProducts)
|
LogDtBigramsUserLast50QueriesMintop2Score
web_meta_pers: 143
Take last 50 query embeddings, Calc dot product with query embedding, sort descending, f = DotProducts[1] (in zero-numeration)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestamp01daysDwt120Less
web_meta_pers: 144
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime less than 120sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestamp01daysDwt120More
web_meta_pers: 145
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 120sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestamp05daysDwt120Less
web_meta_pers: 146
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.5days, dwelltime less than 120sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestamp05daysDwt120More
web_meta_pers: 147
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.5days, dwelltime more than 120sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestamp3daysDwt120Less
web_meta_pers: 148
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=3days, dwelltime less than 120sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestamp3daysDwt120More
web_meta_pers: 149
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=3days, dwelltime more than 120sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestampDays01Dwt30More
web_meta_pers: 150
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 30sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestampDays01Dwt90Less
web_meta_pers: 151
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime less than 90sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestampDays01Dwt300More
web_meta_pers: 152
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.1days, dwelltime more than 300sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestampDays02Dwt600Less
web_meta_pers: 153
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.2days, dwelltime less than 600sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestampDays03Dwt30More
web_meta_pers: 154
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.3days, dwelltime more than 30sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestampDays03Dwt600More
web_meta_pers: 155
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.3days, dwelltime more than 600sec), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedDeltaTimestampDays300Dwt30Less
web_meta_pers: 156
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=300days, dwelltime less than 120sec DWT30), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedQueryDeltaTimestamp003days
web_meta_pers: 157
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=0.03days), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedQueryDeltaTimestamp12days
web_meta_pers: 158
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=1.2days), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedQueryDeltaTimestamp6days
web_meta_pers: 159
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=6days), f = 1 - 2^(-0.2 * value)
|
FadingEmbLogDtBigramsNormalizedQueryDeltaTimestamp14days
web_meta_pers: 160
fadingEmbedding.Norm * CalcFading(fadingEmbedding.FadingCoef, requestTimestamp - fadingEmbedding.LastUpdTimestamp), (model=LogDwellTimeBigrams, fadingCoef=14days), f = 1 - 2^(-0.2 * value)
|