Mastering Modern Time Series Forecasting (Early Access)
The definitive guide to statistical, machine learning, and deep learning forecasting in Python

This book is for people who want forecasting that actually works in the real world — not outdated theory, shallow recipes, or code dumps with no explanation.

Mastering Modern Time Series Forecasting is an end-to-end, practitioner-first guide to building reliable forecasting systems: from foundations and validation to classical models, feature-based ML, deep learning, transformers, and modern foundation time series models (FTSMs).

Written by Valery Manokhin, PhD, MBA, CQF, based on years of building and auditing production forecasting systems that drive real business impact — and seeing exactly how projects fail when evaluation is wrong, assumptions are ignored, or “shiny models” replace engineering discipline.

Early Access is available now. The price will increase as new chapters drop — preorder to lock in lifetime updates.

What You’ll Learn

✅ Foundations that prevent costly mistakes

• What forecast “accuracy” really means
• Proper backtesting, validation, and leakage prevention
• Metric selection, baselines, and decision-aligned evaluation

✅ Classical models, done right

• ARIMA and exponential smoothing with modern, practical interpretation
• When classical methods win — and when they don’t

✅ Machine learning for time series

• Feature engineering and strong ML baselines
• Training workflows that generalize beyond a single dataset

✅ Deep learning & transformers

• Modern architectures with readable, practical Python / PyTorch code
• What works, what’s hype, and how to evaluate fairly

✅ FTSMs: foundation time series models

• Large pre-trained models for time series — “GPT-style” generalization
• How to use them, benchmark them, and avoid common traps

Who This Is For

• Data Scientists & ML Engineers building production forecasting systems
• Analysts & Developers who need a hands-on reference with depth
• Students, educators & researchers seeking a modern, curriculum-friendly guide
• Demand planners & business teams who rely on forecasts for decisions

Why This Book Stands Out

• Starts with evaluation and validation (the part most books get wrong)
• Explains the “why,” not just the “how” — so you can adapt methods to your own data
• Transparent, well-documented code — no black boxes
• Living book with lifetime updates — buy once, keep benefiting as the field evolves
• Everything in one coherent system — classical → ML → deep learning → FTSMs

What You Get

• Instant access to the current Early Access release
• Code examples, datasets, and notebooks (as released)
• Lifetime updates (new chapters, improvements, errata, and bonus content)
• Early access to upcoming bonus chapters and Q&A sessions (when scheduled)

Ready to take your forecasting skills from classical stats to modern deep learning — and from theory to deployment?

👉 Hit “Buy Now” and start mastering forecasting properly.

Applied Conformal Prediction is a comprehensive and practical guide to one of the most powerful and rapidly evolving frameworks in machine learning: Conformal Prediction (CP).

Written by Valery Manokhin, who completed his PhD under Vladimir Vovk, the creator of Conformal Prediction, and has been one of its most prominent advocates for years, this book reflects deep expertise and commitment to the field. Manokhin's widely followed "Awesome Conformal Prediction" repository and his contributions to the global CP community have helped fuel its meteoric rise in research and industry.

Conformal Prediction is quickly becoming a must-have skill for anyone working in high-stakes, production-level AI systems. It provides rigorous, model-agnostic methods for quantifying uncertainty and constructing statistically valid prediction sets with guaranteed coverage. Unlike many traditional approaches, CP offers finite-sample guarantees without requiring unrealistic assumptions.

This book begins with the philosophical and mathematical origins of CP and walks you through its key components: exchangeability, nonconformity scores, prediction regions, inductive and adaptive variants, and beyond. It then explores cutting-edge research on:

• Classification
• Classifier calibration
• Regression
• Time Series and Forecasting (e.g., EnbPI, blockwise CP)
• Deep Learning Integration (NLP, CV, transformers)
• Weighted CP for covariate shift
• Software tools
• And much more

Whether you're a practitioner building risk-sensitive systems or a researcher exploring the limits of statistical inference, Applied Conformal Prediction is your definitive resource.

Preorder now to lock in the lowest price. You'll get early access to chapters as they’re released, and all future updates will be included. The price will increase significantly as more chapters are added.

Probabilistic Forecasting with Conformal Prediction in Python (Early Access)

The Practical Guide to Uncertainty Quantification for Data Science, Machine Learning, and Forecasting

Confident forecasts aren’t just about accuracy — they’re about knowing when you might be wrong.

This book takes you deep into the fast-growing world of probabilistic forecasting and conformal prediction — modern tools that let you move beyond point estimates to deliver prediction intervals, risk measures, and trustworthy AI decisions.

Whether you’re a data scientist, ML engineer, finance professional, or academic researcher, you’ll learn how to:

• Understand the theory behind conformal prediction and probabilistic forecasting — without unnecessary math overload.
• Apply these methods in real-world projects: from demand forecasting to portfolio risk modeling.
• Implement solutions in Python, step-by-step.
• Build forecasting models that communicate uncertainty clearly to decision-makers.