Artem Timoshenko

Recent work centers on using generative AI for customer insights and developing targeting policies for performance marketing.

1. 2026
   Transforming the Voice of the Customer: Large Language Models for Identifying Customer Needs
   Artem Timoshenko, Chengfeng Mao, John R. Hauser · Under review
   With supervised fine-tuning, LLMs can extract customer needs from open-ended feedback on par with professional analysts — bringing voice-of-the-customer research within reach of smaller teams.
2. 2026
   Policy-Aligned Estimation of Conditional Average Treatment Effects
   Artem Timoshenko, Caio Waisman · Under review
   A new framework for estimating CATEs by focusing on the downstream targeting decisions rather than statistical fit alone. We show that standard "plug-in optimization" and "direct policy learning" are not competing paradigms, but limiting cases of the same optimization problem.
3. 2026
   Guided Creativity: AI Intermediation for Enhancing Originality and Quality in Visual Design
   Xuekang Wu, Guy Aridor, Artem Timoshenko · Under review
   AI image tools don't have to flatten design work. With the right workflow, they can improve designer collaborations, lifting both the originality and the quality of human-created visuals. We provide field evidence with professional designers.
4. 2026
   Improving Targeting Policies by Learning Across Marketing Campaigns
   Marat Ibragimov, Duncan Simester, Artem Timoshenko · Under review
   A Bayesian transfer-learning framework that lets firms reuse information across marketing experiments to improve targeting policies, turning experimental databases into a strategic asset.
5. 2026
   In-Store Coupons: A Large-Scale Field Experiment
   Sebastian Gabel, Duncan Simester, Artem Timoshenko · Under review
   A field experiment with 100+ brands shows when in-store coupons actually drive incremental purchases — and provides evidence of store switching behavior.
6. 2025
   A Sample Size Calculation for Training and Certifying Targeting Policies
   Duncan Simester, Artem Timoshenko, Spyros I. Zoumpoulis · Management Science, 71(11), 8995–9868
   Marketers often run field experiments without knowing how much data they need for designing targeting policies. This paper provides guidance for the sample-size calculations for both training a policy and certifying it before deployment.
7. 2024
   How Retailers Became Ad Platforms
   Sebastian Gabel, Duncan Simester, Artem Timoshenko · Harvard Business Review (online), June 17, 2024
   Retail media has become one of advertising's fastest-growing channels. We explain why retailers turned into ad platforms — and discuss how brands can navigate the resulting shifts in budgets and bargaining power.
8. 2023
   Product Aesthetic Design: A Machine Learning Augmentation
   Alex Burnap, John R. Hauser, Artem Timoshenko · Marketing Science, 42(6), 1029–1056
   Generative AI approach that predicts the aesthetic appeal of physical product designs and helps designers iterate toward more attractive concepts. Done in collaboration with a large automotive brand.
9. 2022
   Product Choice with Large Assortments: A Scalable Deep-Learning Model
   Sebastian Gabel, Artem Timoshenko · Management Science, 68(3), 1591–2376
   Most choice models break when assortments get large. This one scales to thousands of SKUs while capturing time-series dynamics for targeting and promotion decisions.
10. 2020
    Efficiently Evaluating Targeting Policies: Improving Upon Champion vs. Challenger Experiments
    Duncan Simester, Artem Timoshenko, Spyros I. Zoumpoulis · Management Science, 66(8), 3412–3424
    Methods that improve statistical efficiency in standard champion-vs-challenger tests for targeting policies.
11. 2020
    Soul and Machine (Learning)
    Davide Proserpio, John R. Hauser, Xiao Liu, Tomomichi Amano, Alex Burnap, Tong Guo, Dokyun (DK) Lee, Randall Lewis, Kanishka Misra, Eric Schwarz, Artem Timoshenko, Lilei Xu, Hema Yoganarasimhan · Marketing Letters, 31(4), 393–404
    A perspective on where machine learning genuinely advances marketing research and where the harder questions remain.
12. 2020
    Targeting Prospective Customers: Robustness of Machine Learning Methods to Typical Data Challenges
    Duncan Simester, Artem Timoshenko, Spyros I. Zoumpoulis · Management Science, 66(6), 2495–2522
    We stress-test ML targeting methods against common empirical challenges firms encounter, and show which approaches survive.
13. 2019
    Is Deep Learning a Game Changer for Marketing Analytics?
    Glen Urban, Artem Timoshenko, Paramveer Dhillon, John R. Hauser · MIT Sloan Management Review, 61(2)
    Deep learning has changed parts of marketing analytics, not all of it. We assess where it actually moves the needle for managers — and where the hype outruns the value.
14. 2019
    How Do Successful Scholars Get Their Best Research Ideas? An Exploration
    Cathy Cao, Xinyu Cao, Matthew Cashman, Madhav Kumar, Artem Timoshenko, Jeremy Yang, Shuyi Yu, Jerry Zhang, Yuting Zhu, Birger Wernerfelt · Marketing Letters, 30(3), 221–232
    Where do the ideas behind successful marketing research papers actually come from? An exploratory study based on interviews with leading scholars.
15. 2019
    Identifying Customer Needs from User-Generated Content
    Artem Timoshenko, John R. Hauser · Marketing Science, 38(1), 1–20
    Machine-learning analysis of online reviews can match traditional interview-based voice-of-the-customer research at a fraction of the cost. The foundation for the LLM-based work above.

I work with marketing and product leaders on AI adoption for consumer insights and targeted marketing — translating recent research into evidence-based decisions.