Further Reading

This is a curated list of recommended further reading — books, papers, datasets, and code repositories that go deeper on each topic, organized by part and chapter. These are suggestions for going further, not the works formally cited in the text; for the book’s curated bibliography see References.

Part 1: Introduction

What is Marketing Science?

  • Provost, F. & Fawcett, T. (2013). Data Science for Business. O’Reilly Media. — Frames data science around business decisions rather than model accuracy — the book’s core stance; worth revisiting here in Part 1.
  • Taddy, M. (2019). Business Data Science: Combining Machine Learning and Economics to Optimize, Automate, and Accelerate Business Decisions. McGraw Hill. — Connects machine learning to business decision-making, closely aligned with Part 1’s thesis.
  • Davenport, T. H. & Harris, J. G. (2007). Competing on Analytics: The New Science of Winning. Harvard Business School Press. — On how organizations actually collect, analyze, and act on data — a fitting introduction beyond “run the analysis.”
  • Agrawal, A., Gans, J. & Goldfarb, A. (2018). Prediction Machines: The Simple Economics of Artificial Intelligence. Harvard Business Review Press. — Prediction is only one input to a decision; pairs well with the “don’t stop at AUC 0.92” message.

Three Characteristics of Marketing Data

  • Pearl, J. & Mackenzie, D. (2018). The Book of Why: The New Science of Cause and Effect. Basic Books. — An intuitive guide to confounding and unobserved causes; supports the “observed data is the tip of the iceberg” framing (also relevant to Part 3).
  • Chan, D. & Perry, M. (2017). “Challenges and Opportunities in Media Mix Modeling.” Google Inc. — Concurrent campaigns, multicollinearity, and extrapolation risk illustrate why marketing data is messy (also cited in Part 6).
  • Muller, J. Z. (2018). The Tyranny of Metrics. Princeton University Press. — On how measurement distorts behavior; relevant to data as a byproduct of operations (and to KPI design in 2.2).

Part 2: Analysis for Better Decisions

Framing the Right Question

  • Shron, M. (2014). Thinking with Data: How to Turn Information into Insights. O’Reilly Media. — A framework for scoping a project, the data it needs, and the problem actually worth solving — the best single fit for this chapter.
  • Hubbard, D. W. (2014). How to Measure Anything: Finding the Value of Intangibles in Business. Wiley. — On reducing a fuzzy business question to something measurable at the precision a decision requires.
  • Rumelt, R. P. (2011). Good Strategy/Bad Strategy: The Difference and Why It Matters. Crown Business. — Bad strategy is vague aspiration; good strategy names the real obstacle — the same discipline applied to problem framing.

Designing KPIs for Diagnosis

  • Farris, P. W., Bendle, N. T., Pfeifer, P. E. & Reibstein, D. J. (2020). Marketing Metrics: The Manager’s Guide to Measuring Marketing Performance. Pearson. — The standard reference for marketing metrics, ROI, and quantifying marketing’s contribution to profit.
  • Croll, A. & Yoskovitz, B. (2013). Lean Analytics: Use Data to Build a Better Startup Faster. O’Reilly Media. — The “One Metric That Matters” idea pairs naturally with building a KPI tree.
  • Goodhart, C. A. E. (1975). “Problems of Monetary Management: The U.K. Experience.” Papers in Monetary Economics. — The origin of Goodhart’s Law: a measure that becomes a target stops being a good measure.
  • Muller, J. Z. (2018). The Tyranny of Metrics. Princeton University Press. — The downside of metrics — not just designing KPIs, but the danger of managing people by them.

Turning Data into Story

  • Knaflic, C. N. (2015). Storytelling with Data: A Data Visualization Guide for Business Professionals. Wiley. — The most natural fit for this chapter; foundational guidance on data visualization and communication.
  • Minto, B. (2009). The Pyramid Principle: Logic in Writing and Thinking. Pearson. — The source of the executive Situation–Complication–Resolution structure, close to this chapter’s storytelling arc.
  • Duarte, N. (2019). DataStory: Explain Data and Inspire Action Through Story. Ideapress Publishing. — Argues a data story should inspire action — a decision story, not a list of findings.
  • Tufte, E. R. (2001). The Visual Display of Quantitative Information. Graphics Press. — The classic on statistical graphics, charts, and tables.
  • Few, S. (2013). Information Dashboard Design: Displaying Data for At-a-Glance Monitoring. Analytics Press. — A practical complement to Knaflic for dashboard and business-review audiences.
  • Wexler, S., Shaffer, J. & Cotgreave, A. (2017). The Big Book of Dashboards: Visualizing Your Data Using Real-World Business Scenarios. Wiley. — Real-world dashboard examples that connect to the outputs shown to decision-makers.

Part 3: Causal Inference for Marketing

Causal Thinking & Selection Bias

  • Pearl, J. & Mackenzie, D. (2018). The Book of Why: The New Science of Cause and Effect. Basic Books. — Accessible introduction to DAGs, do-calculus, and the counterfactual framework.
  • Angrist, J. D. & Pischke, J.-S. (2009). Mostly Harmless Econometrics. Princeton University Press. — The standard reference for the potential outcomes framework and practical identification strategies.
  • Hernán, M. A. & Robins, J. M. (2020). Causal Inference: What If. Chapman & Hall/CRC. — Graduate-level treatment of causal inference from observational and experimental data; freely available online.
  • Cunningham, S. (2021). Causal Inference: The Mixtape. Yale University Press. — Practitioner-friendly coverage of DiD, IV, RDD, and synthetic control with code examples.

A/B Testing: Design and Pitfalls

  • Kohavi, R., Tang, D. & Xu, Y. (2020). Trustworthy Online Controlled Experiments: A Practical Guide to A/B Testing. Cambridge University Press. — The definitive practitioner reference, covering design, analysis, pitfalls, and organizational considerations.
  • Deng, A., Xu, Y., Kohavi, R. & Walker, T. (2013). “Improving the Sensitivity of Online Controlled Experiments by Utilizing Pre-Experiment Data.” WSDM ’13. — The original CUPED paper, showing how pre-experiment covariates reduce variance.
  • Johari, R., Koomen, P., Pekelis, L. & Walsh, D. (2017). “Peeking at A/B Tests: Why It Matters, and What to Do About It.” KDD ’17. — Formalizes the peeking problem and proposes always-valid inference as a solution.

Quasi-Experiments in Practice

  • Angrist, J. D. & Pischke, J.-S. (2009). Mostly Harmless Econometrics. Princeton University Press. — Core reference for DiD, IV, and RDD with accessible derivations.
  • Abadie, A., Diamond, A. & Hainmueller, J. (2010). “Synthetic Control Methods for Comparative Case Studies.” Journal of the American Statistical Association, 105(490), 493–505. — The foundational synthetic control paper.
  • Cattaneo, M. D., Idrobo, N. & Titiunik, R. (2020). A Practical Introduction to Regression Discontinuity Designs. Cambridge Elements. — Covers sharp and fuzzy RDD with the rdrobust package.
  • Cunningham, S. (2021). Causal Inference: The Mixtape. Yale University Press. — Practitioner-oriented treatment of DiD, RDD, and synthetic control with code examples in R and Stata.

Meta-Learners for CATE

  • Künzel, S. R., Sekhon, J. S., Bickel, P. J. & Yu, B. (2019). “Metalearners for Estimating Heterogeneous Treatment Effects Using Machine Learning.” Proceedings of the National Academy of Sciences, 116(10), 4156–4165. — Defines the S/T/X-learner framework and compares performance across settings.
  • Chernozhukov, V. et al. (2018). “Double/Debiased Machine Learning for Treatment and Structural Parameters.” The Econometrics Journal, 21(1), C1–C68. — Introduces DML with cross-fitting to remove regularization bias.
  • EconML — Microsoft’s Python library for CATE estimation (DML, DR-learner, Causal Forest, and more) with DoWhy integration.
  • DoWhy — Causal inference library providing a four-step workflow: model → identify → estimate → refute.

Uplift Modeling: Find the Persuadables

  • Gutierrez, P. & Gérardy, J.-Y. (2017). “Causal Inference and Uplift Modelling: A Review of the Literature.” JMLR Workshop and Conference Proceedings, 67, 1–13. — Comprehensive survey of uplift modeling methods and evaluation metrics.
  • Radcliffe, N. J. & Surry, P. D. (2011). “Real-World Uplift Modelling with Significance-Based Uplift Trees.” White Paper, Stochastic Solutions. — Introduces uplift trees with statistical significance-based splitting criteria.
  • CausalML — Uber’s Python library for uplift modeling and CATE estimation, including UpliftRandomForestClassifier and Qini/AUUC evaluation tools.
  • Diemert, E., Betlei, A., Renaudin, C. & Amini, M.-R. (2018). “A Large Scale Benchmark for Uplift Modeling.” KDD ’18 Workshop. — Describes the Criteo uplift dataset (13M samples) used in benchmarking throughout this chapter.

Part 4: Customer Analytics

Customer Segmentation

  • Bult, J. R. & Wansbeek, T. (1995). “Optimal Selection for Direct Mail.” Marketing Science, 14(4), 378–394. — the foundational paper on optimal selection for direct mail using RFM-based targeting. Establishes the breakeven framework for evaluating segment-targeted campaigns.
  • Provost, F. & Fawcett, T. (2013). Data Science for Business. O’Reilly Media. — comprehensive introduction to data science for business decisions, including practical coverage of segmentation and clustering in a business context.
  • Vizard, S. (2019). “P&G shifts from targeting ‘generic demographics’ to ‘smart audiences’.” Marketing Week, July 30, 2019.
  • Marketing Week (2019). “Why behaviour beats demographics when it comes to segmentation.” April 15, 2019.

Customer Lifetime Value Modeling

Part 5: Commercial Analytics

Commercial Metrics

  • Byron Sharp, How Brands Grow (2010) — the empirical case for penetration-driven growth.
  • Tan, Steinbach, & Kumar, Introduction to Data Mining — chapter on association analysis for a deeper treatment of support, confidence, and lift.

Price Elasticity and Pricing Decisions

  • Hoch, S. J., Kim, B., Montgomery, A. L., & Rossi, P. E. (1995). Determinants of store-level price elasticity. Journal of Marketing Research, 32(1), 17–29.
  • Tellis, G. J. (1988). The price elasticity of selective demand: A meta-analysis of econometric models of sales. Journal of Marketing Research, 25(4), 331–341.
  • Hermann Simon, Confessions of the Pricing Man (2015) — accessible treatment of pricing strategy, written by the founder of Simon-Kucher.
  • The JCPenney “Fair and Square” pricing case — a cautionary tale about eliminating promotions without understanding reference price effects. Customers revolted not because the new prices were higher, but because the feeling of getting a deal disappeared.

Product Assortment Optimization

  • Kök, A. G., Fisher, M. L., & Vaidyanathan, R. (2015). “Assortment Planning: Review of Literature and Industry Practice.” In Retail Supply Chain Management, Springer. — The comprehensive academic review of assortment optimization methods.
  • Iyengar, S. S., & Lepper, M. R. (2000). “When Choice Is Demotivating: Can One Desire Too Much of a Good Thing?” Journal of Personality and Social Psychology. — The original “jam study.” Influential but contested.
  • Scheibehenne, B., Greifeneder, R., & Todd, P. M. (2010). “Can There Ever Be Too Many Options? A Meta-Analytic Review of Choice Overload.” Journal of Consumer Research. — The meta-analysis that found the average choice-overload effect is close to zero, with high variability across contexts. Treat the paradox of choice as a hypothesis to test, not a universal law.
  • Train, K. E. (2009). Discrete Choice Methods with Simulation, 2nd ed., Cambridge University Press. — The standard textbook for MNL and Mixed Logit. Free online at https://eml.berkeley.edu/books/choice2.html.
  • pylogit (Python) and xlogit (Python, GPU-accelerated) — accessible libraries for discrete choice modeling.

Demand Forecasting

  • Hyndman, R. J., & Athanasopoulos, G., Forecasting: Principles and Practice (3rd ed.) — free online at otexts.com/fpp3. The standard reference for time-series forecasting. Chapters on ETS, ARIMA, and hierarchical reconciliation are particularly relevant.
  • Nixtla open-source libraries: statsforecast, mlforecast, hierarchicalforecast — fast, scalable, well-documented. The unified unique_id / ds / y format is a genuine productivity advantage.
  • Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2022). M5 accuracy competition: Results, findings, and conclusions. International Journal of Forecasting. — The competition that demonstrated gradient boosting’s advantage over statistical models for large-scale retail forecasting.
  • Ansari, A. F., et al. (2024). Chronos: Learning the Language of Time Series. — The architecture and pretraining approach behind Chronos 2. Relevant for understanding zero-shot forecasting.
  • Olivares, K. G., et al. (2022). HierarchicalForecast: A Reference Framework for Hierarchical Forecasting in Python. — Theory and implementation of MinTrace, ERM, and other reconciliation methods.
  • Fildes, R., & Goodwin, P. (2007). Against your better judgment? How organizations can improve their use of management judgment in forecasting. Interfaces, 37(6), 570–576. — The evidence on human override bias and FVA.
  • GIFT-Eval (Salesforce Research). github.com/SalesforceAIResearch/gift-eval — A benchmark for fair comparison of Foundation Models on time-series tasks.

Part 6: Media Investment and Optimization

Attribution: Concepts and Limits

  • Google. “About Data-Driven Attribution.” Google Ads Help.
  • Berman, R. (2018). “Beyond the Last Touch: Attribution in Online Advertising.” Marketing Science, 37(5), 771-792.
  • Dalessandro, B. et al. (2012). “Causally Motivated Attribution for Online Advertising.” ADKDD ’12.

MMM Fundamentals

  • Jin, Y., Wang, Y., Sun, Y., Chan, D. & Koehler, J. (2017). “Bayesian Methods for Media Mix Modeling with Carryover and Shape Effects.” Google Inc. — Google’s paper on Bayesian MMM with hierarchical priors and geo-level data, the methodological foundation for Meridian.
  • Chan, D. & Perry, M. (2017). “Challenges and Opportunities in Media Mix Modeling.” Google Inc. — Companion paper covering common pitfalls in MMM (multicollinearity, extrapolation, insufficient variation) and how to address them.
  • Meridian — Google’s actively maintained Bayesian MMM library (successor to LightweightMMM), used in the walkthrough in this chapter.
  • Robyn — Meta’s open-source MMM library using Ridge regression with hyperparameter optimization via Nevergrad.
  • PyMC-Marketing — Bayesian MMM and CLV library built on PyMC, with flexible model specification and saturation/adstock transforms.

Budget Optimization

  • Jin, Y., Wang, Y., Sun, Y., Chan, D. & Koehler, J. (2017). “Bayesian Methods for Media Mix Modeling with Carryover and Shape Effects.” Google Inc. — Describes the Bayesian MMM framework that underpins Meridian’s budget optimizer, including the posterior-based optimization approach.
  • Chan, D. & Perry, M. (2017). “Challenges and Opportunities in Media Mix Modeling.” Google Inc. — Discusses practical challenges in MMM-based optimization, including extrapolation risks and multicollinearity.
  • Meridian Budget Optimization Guide — Documentation for Meridian’s BudgetOptimizer, including per-channel constraints and scenario analysis.
  • Fischer, M., Albers, S., Wagner, N. & Frie, M. (2011). “Dynamic Marketing Budget Allocation Across Countries, Products, and Marketing Activities.” Marketing Science, 30(4), 568–585. — Multi-level budget allocation framework with diminishing returns and cross-effects.

Calibrating MMM with Experiments

  • Jin, Y., Wang, Y., Sun, Y., Chan, D. & Koehler, J. (2017). “Bayesian Methods for Media Mix Modeling with Carryover and Shape Effects.” Google Inc. — Google’s Bayesian MMM paper describing the prior calibration framework that Meridian implements.
  • Vaver, J. & Koehler, J. (2011). “Measuring Ad Effectiveness Using Geo Experiments.” Google Inc. — The foundational paper on geo-lift testing methodology.
  • Brodersen, K. H., Gallusser, F., Koehler, J., Remy, N. & Scott, S. L. (2015). “Inferring Causal Impact Using Bayesian Structural Time-Series Models.” The Annals of Applied Statistics, 9(1), 247–274. — Bayesian structural time-series approach to geo experiments, an alternative to DID.
  • Meridian Calibration Guide — Official documentation for roi_m priors and roi_calibration_period.
  • GeoLift — Open-source R package for designing and analyzing geo-lift experiments.