[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123463-en":3,"doc-seo-123463-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123463,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Double Machine Learning at Scale to Predict Causal Impact of Customer Actions","Causal Impact (CI) of customer actions is used to guide both short- and long-term investment decisions across industries. This paper applies a Double Machine Learning (DML) methodology to estimate CI for hundreds of customer actions across hundreds of millions of customers. DML is operationalized using a Spark-based causal ML library with JSON-driven model configuration to compute population-level and customer-level CI values with confidence intervals. Validation shows 2.2% improvement over baseline methods and a 2.5× reduction in computational time, enabling scalable CI experimentation and accessibility for partner teams.","arXiv :2409 .02332v 1 [ cs .LG] 3 Sep 2024  \nDouble Machine Learning at Scale to Predict Causal Impact of Customer Actions  \nSushant More [0000−0002−3746−2431]􀀀, Priya Kotwal[0009−0004−6599−359X], Sujith Chappidi [0009−0009−3310−6067], Dinesh Mandalapu [0009−0007−2984−859X], and Chris Khawand [0009−0000−5283−9391]  \nAmazon, Seattle WA, USA  \n{morsusha,kotwalp,jcchappi,mandalap,[khawandc}@amazon.com](khawandc}@amazon.com)  \nAbstract. Causal Impact (CI) of customer actions are broadly used across the industry to inform both short- and long-term investment decisions of various types. In this paper, we apply the double machine learning (DML) methodology to estimate the CI values across 100s of customer actions of business interest and 100s of millions of customers.  \nWe operationalize DML through a causal ML library based on Spark with a flexible, JSON-driven model configuration approach to estimate CI at scale (i.e., across hundred of actions and millions of customers) . We outline the DML methodology and implementation, and associated benefits over the traditional potential outcomes based CI model. We show populationlevel as well as customer-level CI values along with confidence intervals.  \nThe validation metrics show a 2.2% gain over the baseline methods and a  \n2.5X gain in the computational time. Our contribution is to advance the scalable application of CI, while also providing an interface that allows faster experimentation, cross-platform support, ability to onboard new use cases, and improves accessibility of underlying code for partner teams.  \nKeywords: Double Machine Learning · Potential Outcomes · Heterogeneous treatment effect · Invserse propenity weighting · Placebo tests.  \n1 Introduction  \nCausal Impact (CI) is a measure of the incremental change in a customer’s outcomes (usually spend or profit) from a customer event or action (e.g, signing up for a paid membership) . CI values are used across the industry as important signals of long-term value for multiple decisions, such as marketing content ranking to long-term investment decisions.  \nBusiness teams are typically interested in calculating CI values for relevant actions that a customer participates in. Some examples include customer actions such as ‘first purchase in category X’, ‘first Y stream’, or ‘sign up for program Z ’1. The CI values are leveraged by partner teams to understand and improve the value they generate. For many of these customer actions, we are unable to  \n1 We use placeholder X ,Y ,Z to maintain business confidentiality  \n2 S. More et al.  \nconduct A/B experiments due to practical or legal constraints. CI values are thus estimated off of observational data, effectively leveraging rich customer data to isolate causal relationships in the absence of a randomized experiment.  \nIn this paper, we provide results for average treatment effects and conditional average treatment effects (i.e., customer-level CI values) estimated using a variant on the Double Machine Learning (DML) methodology [1] . The paper is arranged as follows. In Sec. 2, we give a brief overview of the use and scale of CI in the industry. In Sec. 2.1, we introduce the traditional system used for calculating CI values. We also discuss the shortcomings of the traditional method and the advantages of moving to a DML-based method for calculating CI.  \nSec. 3 covers the details of our DML implementation for calculating CI values. Our contributions include improving the robustness of CI estimates through inverse propensity weighting, adding the ability to produce heterogeneous CI values, implementing customer-level confidence intervals with various assumptions, and making available the JSON Machine Learning interface to accelerate experimentation. We present results in Sec. 4 for a few customer actions and conclude with the takeaways and ideas for future work in Sec. 6.  \n2 Causal impact estimation in industry  \nCausal impact estimation drives a large number of business decisions ac","cbCaieY1ueKIJVsQ","https://ap.wps.com/l/cbCaieY1ueKIJVsQ","pdf",973116,1,16,"English","en",105,"# Introduction\n## Causal Impact (CI) and observational estimation\n## Double Machine Learning (DML) overview\n# Causal impact estimation in industry\n## CI: Potential Outcomes framework\n## Propensity binning\n## Regression adjustment","[{\"question\":\"What does Causal Impact (CI) measure in this paper?\",\"answer\":\"CI measures the incremental change in a customer’s outcomes (e.g., spend or profit) caused by a specific customer event or action, compared with the counterfactual where the action was not taken.\"},{\"question\":\"How is Double Machine Learning (DML) used to estimate CI at scale?\",\"answer\":\"The paper implements a DML-based approach using a Spark causal ML library, driven by flexible JSON model configurations, to estimate CI across many actions and millions of customers.\"},{\"question\":\"What benefits does the proposed method provide over traditional potential-outcomes CI modeling?\",\"answer\":\"Results report population- and customer-level CI with confidence intervals, robustness improvements via inverse propensity weighting, support for heterogeneous effects, and performance gains: 2.2% improvement in validation and 2.5× faster computation time.\"}]","Double Machine Learning at Scale to Predict Causal Impact of Customer Actions | PDF",1785816659,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"double-machine-learning-at-scale-to-predict-causal-impact-of-customer-actions","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/double-machine-learning-at-scale-to-predict-causal-impact-of-customer-actions/123463/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does Causal Impact (CI) measure in this paper?","Question",{"text":75,"@type":76},"CI measures the incremental change in a customer’s outcomes (e.g., spend or profit) caused by a specific customer event or action, compared with the counterfactual where the action was not taken.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is Double Machine Learning (DML) used to estimate CI at scale?",{"text":80,"@type":76},"The paper implements a DML-based approach using a Spark causal ML library, driven by flexible JSON model configurations, to estimate CI across many actions and millions of customers.",{"name":82,"@type":73,"acceptedAnswer":83},"What benefits does the proposed method provide over traditional potential-outcomes CI modeling?",{"text":84,"@type":76},"Results report population- and customer-level CI with confidence intervals, robustness improvements via inverse propensity weighting, support for heterogeneous effects, and performance gains: 2.2% improvement in validation and 2.5× faster computation time.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]