Chapter 42 Further Reading

An annotated bibliography for continued learning beyond this book. Resources are organized by topic area and rated for difficulty: (Beginner), (Intermediate), or (Advanced).

Prediction Markets: Theory and Practice

Arrow, K. J., et al. (2008). "The Promise of Prediction Markets." Science, 320(5878), 877-878. A short, influential letter signed by leading economists arguing for the deregulation of prediction markets. Essential reading for understanding the policy debate. (Beginner)

Wolfers, J., & Zitzewitz, E. (2004). "Prediction Markets." Journal of Economic Perspectives, 18(2), 107-126. A comprehensive survey of prediction market theory, evidence, and applications. Covers information aggregation, market efficiency, and comparisons with polls and expert forecasts. (Intermediate)

Hanson, R. (2003). "Combinatorial Information Market Design." Information Systems Frontiers, 5(1), 107-119. Robin Hanson's seminal paper on logarithmic market scoring rules (LMSR), the mathematical foundation for many automated market makers used in prediction markets. (Advanced)

Manski, C. F. (2006). "Interpreting the Predictions of Prediction Markets." Economics Letters, 91(3), 425-429. A critical analysis of whether prediction market prices truly represent probabilities. Manski argues that risk preferences and other factors can distort the probability interpretation. Important for understanding the limitations of your model's inputs. (Advanced)

Berg, J., Nelson, F., & Rietz, T. (2008). "Prediction Market Accuracy in the Long Run." International Journal of Forecasting, 24(2), 285-300. Long-term analysis of the Iowa Electronic Markets' predictive accuracy for US presidential elections. Shows that prediction markets consistently outperform polls, especially far from election day. (Intermediate)

Probability, Calibration, and Scoring Rules

Tetlock, P. E., & Gardner, D. (2015). Superforecasting: The Art and Science of Prediction. Crown. Essential reading on what makes some forecasters better than others. The Good Judgment Project's findings on calibration, updating, and cognitive style directly inform how to build better prediction models. (Beginner)

Gneiting, T., & Raftery, A. E. (2007). "Strictly Proper Scoring Rules, Prediction, and Estimation." Journal of the American Statistical Association, 102(477), 359-378. The definitive mathematical treatment of proper scoring rules. Explains why Brier score and log loss are proper, and the implications for model evaluation. (Advanced)

Dawid, A. P. (1982). "The Well-Calibrated Bayesian." Journal of the American Statistical Association, 77(379), 605-610. Foundational paper on calibration — the relationship between predicted probabilities and observed frequencies. (Advanced)

Niculescu-Mizil, A., & Caruana, R. (2005). "Predicting Good Probabilities with Supervised Learning." ICML 2005. Practical guide to calibrating machine learning models, comparing Platt scaling, isotonic regression, and other methods. Directly applicable to the model training pipeline. (Intermediate)

Trading Strategies and Portfolio Management

Kelly, J. L. (1956). "A New Interpretation of Information Rate." Bell System Technical Journal, 35(4), 917-926. The original Kelly criterion paper. While the mathematical formalism is from information theory, the implications for optimal bet sizing are profound and timeless. (Advanced)

Thorp, E. O. (2006). The Kelly Capital Growth Investment Criterion: Theory and Practice. World Scientific. A comprehensive collection of papers on the Kelly criterion, including practical modifications (fractional Kelly, constraints) that we use in the capstone system. (Intermediate)

Poundstone, W. (2005). Fortune's Formula: The Untold Story of the Scientific Betting System That Beat the Casinos and Wall Street. Hill and Wang. An engaging popular account of the Kelly criterion's history, from Claude Shannon's information theory to Ed Thorp's blackjack and Wall Street exploits. (Beginner)

Lopez de Prado, M. (2018). Advances in Financial Machine Learning. Wiley. The most practical book on applying machine learning to financial trading. Covers backtesting pitfalls, feature importance, cross-validation for financial data, and portfolio construction. Many of our backtesting design decisions draw from this work. (Advanced)

Chan, E. (2009). Quantitative Trading: How to Build Your Own Algorithmic Trading Business. Wiley. Practical guide to building trading systems, covering strategy development, backtesting, risk management, and deployment. While focused on traditional financial markets, the principles apply directly to prediction markets. (Intermediate)

Machine Learning for Prediction

Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning, 2nd ed. Springer. The classic ML textbook, freely available online. Covers all the algorithms used in our ensemble (logistic regression, boosting, random forests) with rigorous mathematical foundations. (Advanced)

Chen, T., & Guestrin, C. (2016). "XGBoost: A Scalable Tree Boosting System." KDD 2016. The paper introducing XGBoost, the gradient boosting framework used in our ensemble model. Explains the algorithmic innovations that make it fast and effective. (Intermediate)

Lundberg, S. M., & Lee, S.-I. (2017). "A Unified Approach to Interpreting Model Predictions." NeurIPS 2017. Introduces SHAP values for model interpretability. Essential for understanding why your model makes specific predictions, which is critical for debugging and trust. (Intermediate)

Bergstra, J., & Bengio, Y. (2012). "Random Search for Hyper-Parameter Optimization." JMLR, 13, 281-305. Demonstrates that random search is more efficient than grid search for hyperparameter tuning. A practical insight for model training pipeline optimization. (Intermediate)

Blockchain and Decentralized Finance

Buterin, V. (2014). Ethereum Whitepaper: A Next-Generation Smart Contract and Decentralized Application Platform. The foundational document for Ethereum, the blockchain platform that underpins most decentralized prediction markets. (Intermediate)

Gnosis. (2017). Conditional Tokens Framework Whitepaper. Technical specification for the conditional token standard (ERC-1155) used by Polymarket and other prediction market platforms. Understanding this is essential for on-chain integration. (Advanced)

Peterson, J. (2015). Augur: a Decentralized Oracle and Prediction Market Platform. Augur White Paper. The pioneering decentralized prediction market design. While Augur itself has evolved, the design principles (decentralized oracle, REP token, dispute resolution) influenced the entire space. (Intermediate)

Harvey, C. R., Ramachandran, A., & Santoro, J. (2021). DeFi and the Future of Finance. Wiley. Comprehensive overview of decentralized finance, including prediction markets, AMMs, and oracle systems. Good context for understanding where prediction markets fit in the broader DeFi ecosystem. (Intermediate)

Risk Management

Taleb, N. N. (2007). The Black Swan: The Impact of the Highly Improbable. Random House. Essential reading on tail risk and the limitations of normal distribution assumptions. Reminds us that our risk management system must handle events that our models consider "impossible." (Beginner)

Taleb, N. N. (2012). Antifragile: Things That Gain from Disorder. Random House. Extends the Black Swan framework to argue for systems that benefit from volatility. The capstone system's circuit breakers and fractional Kelly sizing are antifragile design choices. (Beginner)

McNeil, A. J., Frey, R., & Embrechts, P. (2015). Quantitative Risk Management: Concepts, Techniques and Tools, revised ed. Princeton University Press. The definitive academic textbook on financial risk management. Covers Value-at-Risk, Expected Shortfall, copulas, and extreme value theory. (Advanced)

System Design and Software Engineering

Kleppmann, M. (2017). Designing Data-Intensive Applications. O'Reilly. The best book on designing reliable, scalable, and maintainable data systems. Covers databases, stream processing, and distributed systems — all relevant to scaling a trading system. (Intermediate)

Newman, S. (2021). Building Microservices, 2nd ed. O'Reilly. Guide to microservice architecture, which is the natural evolution of the modular monolith built in this capstone. When your system grows beyond a single process, this book shows you how to decompose it. (Intermediate)

Beyer, B., et al. (2016). Site Reliability Engineering: How Google Runs Production Systems. O'Reilly. Google's approach to running reliable production systems. The monitoring, alerting, and incident response principles directly apply to operating a trading bot. Freely available online. (Intermediate)

Regulation and Ethics

Sunstein, C. R. (2006). "Infotopia: How Many Minds Produce Knowledge." Oxford University Press. Explores how group decision-making mechanisms, including prediction markets, aggregate information. Discusses the potential and limitations of collective intelligence. (Beginner)

CFTC. (2024-ongoing). Event Contracts rulemaking and advisory documents. The US Commodity Futures Trading Commission's evolving regulatory framework for event contracts (prediction markets). Essential reading for anyone operating in the US market. Available on cftc.gov. (Intermediate)

Abramowicz, M. (2003). "Information Markets, Administrative Decisionmaking, and Predictive Cost-Benefit Analysis." University of Chicago Law Review, 71, 933. Legal analysis of prediction markets and their potential role in government decision-making. Provides important context for the regulatory landscape. (Advanced)

Online Resources and Communities

Metaculus (metaculus.com) Active forecasting community with thousands of questions. Excellent for practicing calibration and comparing your predictions against a crowd. Free to use.

Good Judgment Open (gjopen.com) The public counterpart to the Good Judgment Project. Practice forecasting on geopolitical questions and track your calibration over time.

Manifold Markets (manifold.markets) A play-money prediction market platform that allows anyone to create markets. Good for experimentation and learning market mechanics without financial risk.

LessWrong (lesswrong.com) Rationalist community with extensive writing on forecasting, calibration, decision theory, and prediction markets. The discussion threads on forecasting techniques are particularly valuable.

Polymarket Learn (learn.polymarket.com) Polymarket's educational resources, including API documentation, trading guides, and market creation tutorials.

For readers who want to continue deepening their expertise, we recommend the following sequence:

  1. Immediate next steps: Read Superforecasting (Tetlock) and practice on Metaculus for 3 months to sharpen your calibration.

  2. Deepen ML skills: Work through The Elements of Statistical Learning (Hastie et al.) and experiment with advanced models on your trading system.

  3. Study risk management: Read The Black Swan and Quantitative Risk Management to understand the limits of your current risk framework.

  4. Understand the ecosystem: Read the regulatory documents and DeFi and the Future of Finance to understand where prediction markets are heading.

  5. Scale your system: Read Designing Data-Intensive Applications when your system outgrows a single machine.

  6. Contribute to the field: Consider publishing your findings, contributing to open-source prediction market tools, or participating in forecasting tournaments.