Several people have asked me about my work at JD.com during 2017-2019, when I was on leave from Stanford. This page describes some of my work and the research that came out of this time. I worked in JD’s Silicon Valley office as Chief Scientist for Business Strategy. I am currently affiliated with JD’s Intelligent Ads Group.

JD.com Overview

JD.com is China’s second largest ecommerce company. JD’s 2019 revenues of USD 82.9B makes it China’s largest internet company by revenue: see here for more facts about the company.

Broad Focus

My role was focused on using marketing science and applied econometrics to drive growth for JD and its partner brands in China, leveraging JD’s data assets and AI-driven technology platform. This article describes at a high level some of the goals of the broad effort: https://finance.sina.cn/2018-10-18/detail-ifxeuwws5653433.d.html (translation required). See here and here for some broad overviews of the JD Marketing 360 platform.

Together with Paul Yan, President of JD Business Growth, engineering leaders Jack Lin and Lei Wu, and our incredible data science and economics team,  I developed products related to eCommerce marketing, pricing and advertising for improved brand-building, monetization and ad-strategy for JD and participating brands.

Ad-Experimentation Platform

One effort involved developing an external facing ad-experimentation platform for the JD ad-business. The platform comprises a set of products that together facilitate scalable, self-serve experimentation by advertisers to evaluate and enhance their advertising campaigns on JD. Together, the idea behind these products is for a publisher to provide experimentation “as a service” to its participating firms.

Specific Products

A few specific products developed for the platform are described below. These products are currently deployed or in production on JZT (https://jzt.jd.com/), JD’s campaign management platform.

  • JD Multi Touch Attribution (MTA) uses a Recurrent Neural Network trained on granular user data along with Shapley Values to develop a data-driven attribution system to assess campaign performance for advertisers on JD.  A related product,  “Path to Purchase,” visualizes consumer click-steams on JD so as to provide more data-driven context to the reported attribution. This article provides an overview: http://papers.adkdd.org/2019/papers/adkdd19-du-causally.pdf.
  • Touchpoint Mix Modeling (TMM) develops an advertiser-facing product based on new experimentation-optimization algorithms for campaign-level automated bidding and budget allocation built on JD MTA. Marketing campaign automation is increasingly important on digital platforms in lieu of the complexity of managing campaigns, and this system helps achieve that. See here for a product overview.
  • JD Conversion Lift for RTB develops a system and experimental design for measuring ad-lifts in an real-time bidding (RTB) environment from a publisher’s perspective. The publisher controls the ad-auction mechanism and the system exploits knowledge of the publisher’s real-time auction-queue. A new aspect of the framework is it facilitates simultaneous parallel experimentation across multiple competitors in such an environment, defining the relevant treatment effects. This article provides an overview: https://arxiv.org/abs/1903.11198.
  • JD Conversion Lift for AdX develops a system and experimental design for measuring ad-lift in an real-time bidding (RTB) environment from a Demand Side Platform (DSP’s) perspective. The DSP, of which JD is an example, submits bids on behalf of advertisers into an external ad-exchange (AdX). It cannot control the AdX’s auction or observe its auction-queue. The framework facilitates experimentation in such an environment by randomizing the bids submitted by the DSP into the AdX auction. The randomization is implemented adaptively, via a contextual bandit, so that the optimal bidding policy is also learned alongside inference of the ad-lift, so that the algorithm simultaneously delivers on the advertiser’s payoff-maximizing goal and her causal-inference goals. This article provides an overview: https://arxiv.org/abs/1908.08600.
  • JD Comparison Lift develops a system to help an advertiser designing a campaign to discover via online experimentation, a creative-target audience combination that provides her the highest expected payoff. The target audiences can be complex, potentially overlapping with each other, and the creatives can be any type of media (picture, video, text etc.). The algorithm is set up as a contextual bandit that adaptively allocates traffic during the test so as to minimize the cost to the advertiser from experimentation.  Broad overviews here and here.
  • Digital Couponing is particularly powerful in eCommerce. Digital coupons are complex pricing contracts that enable differential pricing to be implemented at scale in a way that is targeted, personalized, with individualized deadlines, product scope and contactual features, while reducing psychological reactance from consumers to price variation. JD’s couponing platform delivers a wide variety of coupons and vouchers to users.  A paper that leverages field experiments developed to evaluate the efficacy of JD’s consumption vouchers as a policy tool to stimulate household spending and help mitigate the economic costs of COVID-19 is here.

Overall, by leveraging causal inference, experimentation, and machine learning with micro-data in a scalable way, these products help advertisers better measure and implement their digital marketing campaigns when working with publishers and to better optimize their pricing and advertising strategies.