book

Probabilistic Machine Learning for Finance and Investing

by Deepak K. Kanungo

August 2023

Intermediate to advanced

264 pages

English

O'Reilly Media, Inc.

Book available

Read now

Unlock full access

Who Should Read This Book?Why I Wrote This BookNavigating This BookConventions Used in This BookUsing Code ExamplesO’Reilly Online LearningHow to Contact UsAcknowledgments
Finance Is Not PhysicsAll Financial Models Are Wrong, Most Are UselessThe Trifecta of Modeling ErrorsErrors in Model SpecificationErrors in Model Parameter EstimatesErrors from the Failure of a Model to Adapt to Structural ChangesProbabilistic Financial ModelsFinancial AI and MLProbabilistic MLProbability DistributionsKnowledge IntegrationParameter InferenceGenerative EnsemblesUncertainty AwarenessSummaryReferencesFurther Reading
The Monty Hall ProblemAxioms of ProbabilityInverting ProbabilitiesSimulating the SolutionMeaning of ProbabilityFrequentist ProbabilityEpistemic ProbabilityRelative ProbabilityRisk Versus Uncertainty: A Useless DistinctionThe Trinity of UncertaintyAleatory UncertaintyEpistemic UncertaintyOntological UncertaintyThe No Free Lunch TheoremsInvesting and the Problem of InductionThe Problem of Induction, NFL Theorems, and Probabilistic Machine LearningSummaryReferences
Monte Carlo Simulation: Proof of ConceptKey Statistical ConceptsMean and VarianceExpected Value: Probability-Weighted Arithmetic MeanWhy Volatility Is a Nonsensical Measure of RiskSkewness and KurtosisThe Gaussian or Normal DistributionWhy Volatility Underestimates Financial RiskThe Law of Large NumbersThe Central Limit TheoremTheoretical Underpinnings of MCSValuing a Software ProjectBuilding a Sound MCSSummaryReferences
The Inverse FallacyNHST Is Guilty of the Prosecutor’s FallacyThe Confidence GameSingle-Factor Market Model for EquitiesSimple Linear Regression with StatsmodelsConfidence Intervals for Alpha and BetaUnveiling the Confidence GameErrors in Making Probabilistic Claims About Population ParametersErrors in Making Probabilistic Claims About a Specific Confidence IntervalErrors in Making Probabilistic Claims About Sampling DistributionsSummaryReferencesFurther Reading
Investigating the Inverse Probability RuleEstimating the Probability of Debt DefaultGenerating Data with Predictive Probability DistributionsSummaryFurther Reading
AI Systems: A Dangerous Lack of Common SenseWhy MLE Models Fail in FinanceAn MLE Model for Earnings ExpectationsA Probabilistic Model for Earnings ExpectationsMarkov Chain Monte Carlo SimulationsMarkov ChainsMetropolis SamplingSummaryReferences
MLE Regression ModelsMarket ModelModel AssumptionsLearning Parameters Using MLEQuantifying Parameter Uncertainty with Confidence IntervalsPredicting and Simulating Model OutputsProbabilistic Linear EnsemblesPrior Probability Distributions P(a, b, e)Likelihood Function P(Y| a, b, e, X)Marginal Likelihood Function P(Y|X)Posterior Probability Distributions P(a, b, e| X, Y)Assembling PLEs with PyMC and ArviZDefine Ensemble Performance MetricsAnalyze Data and Engineer FeaturesDevelop and Retrodict Prior EnsembleTrain and Retrodict Posterior ModelTest and Evaluate Ensemble PredictionsSummaryReferencesFurther Reading
Probabilistic Inference and Prediction FrameworkProbabilistic Decision-Making FrameworkIntegrating SubjectivityEstimating LossesMinimizing LossesRisk ManagementCapital PreservationErgodicityGenerative Value at RiskGenerative Expected ShortfallGenerative Tail RiskCapital AllocationGambler’s RuinExpected Valuer’s RuinModern Portfolio TheoryMarkowitz Investor’s RuinKelly CriterionKelly Investor’s RuinSummaryReferencesFurther Reading

Content preview from Probabilistic Machine Learning for Finance and Investing

About the Author

Deepak K. Kanungo is an algorithmic derivatives trader, instructor, and CEO of Hedged Capital LLC, an AI-powered proprietary trading company that he founded in 2009. Since 2019, Deepak has taught tens of thousands of O’Reilly Media subscribers worldwide the concepts, processes, and machine learning technologies for algorithmic trading, investing, and finance with Python.

In 2005, long before machine learning was an industry buzzword, Deepak invented a probabilistic machine learning method and software system for managing the risks and returns of project portfolios. It is a unique probabilistic framework that has been cited by IBM and Accenture, among others.

Previously, Deepak was a financial advisor at Morgan Stanley, a Silicon Valley fintech entrepreneur, a director in the Global Planning Department at Mastercard International, and a senior analyst with Diamond Technology Partners. He was educated at Princeton University (astrophysics) and the London School of Economics (finance and information systems). He is the instructor for the O’Reilly course Hands-On Algorithmic Trading With Python.