Preveja as compras dos visitantes usando um modelo de classificação no BigQuery ML avaliações

shashwat k. · Revisado há almost 2 years

Ashif K. · Revisado há almost 2 years

Pʀᴀʙᴀʟ P. · Revisado há almost 2 years

Ricky R. · Revisado há almost 2 years

HARI MEGHANA K. · Revisado há almost 2 years

Two queries are incorrect unable to complete it, please verify and correct. 1st one: SELECT * FROM ml.PREDICT(MODEL `ecommerce.classification_model_2`, ( WITH all_visitor_stats AS ( SELECT fullvisitorid, IF(COUNTIF(totals.transactions > 0 AND totals.newVisits IS NULL) > 0, 1, 0) AS will_buy_on_return_visit FROM `data-to-insights.ecommerce.web_analytics` GROUP BY fullvisitorid ) SELECT CONCAT(fullvisitorid, '-',CAST(visitId AS STRING)) AS unique_session_id, 2nd: SELECT roc_auc, CASE WHEN roc_auc > .9 THEN 'good' WHEN roc_auc > .8 THEN 'fair' WHEN roc_auc > .7 THEN 'decent' WHEN roc_auc > .6 THEN 'not great' ELSE 'poor' END AS model_quality FROM ML.EVALUATE(MODEL ecommerce.classification_model, ( SELECT * EXCEPT(fullVisitorId) FROM # features (SELECT fullVisitorId, IFNULL(totals.bounces, 0) AS bounces, IFNULL(totals.timeOnSite, 0) AS time_on_site FROM `data-to-insights.ecommerce.web_analytics` WHERE totals.newVisits = 1 AND date BETWEEN '20170501' AND '20170630') # eval on 2 months JOIN (SELECT fullvisitorid, IF(COUNTIF(totals.transactions > 0 AND totals.newVisits IS NULL) > 0, 1, 0) AS will_buy_on_return_visit FROM `data-to-insights.ecommerce.web_a

Ravi Kumar D. · Revisado há almost 2 years

Shatarupa S. · Revisado há almost 2 years

Anwesa H. · Revisado há almost 2 years

Prashant G. · Revisado há almost 2 years

nice

Baldev R. · Revisado há almost 2 years

Done

Wey Jie G. · Revisado há almost 2 years

sanchari K. · Revisado há almost 2 years

Aashish T. · Revisado há almost 2 years

Renaldi A. · Revisado há almost 2 years

Digant M. · Revisado há almost 2 years

VELDANDA R. · Revisado há almost 2 years

Tamal A. · Revisado há almost 2 years

Rakesh A. · Revisado há almost 2 years

Perfeito !

Rogério S. · Revisado há almost 2 years

Cool lab.

Armin M. · Revisado há almost 2 years

Mulyana A. · Revisado há almost 2 years

Nur A. · Revisado há almost 2 years

Shaikh C. · Revisado há almost 2 years

Asdrubal R. · Revisado há almost 2 years

Amaan P. · Revisado há almost 2 years