Prediction revisited : the importance of observation / Megan Czasonis, Mark Kritzman, David Turkington.

Format:

Book

Author/Creator:

Czasonis, Megan, author.

Kritzman, Mark P., author.

Turkington, David, 1983- author.

Language:

English

Subjects (All):

Predictive analytics.

Business enterprises--Finance.

Business enterprises.

Machine learning.

Physical Description:

1 online resource (240 pages)

Place of Publication:

Hoboken, New Jersey : John Wiley & Sons, Incorporated, [2022]

Summary:

"Prediction Revisited is a ground-breaking book for financial analysts and researchers--as well as data scientists in other disciplines--to reconsider classical statistics and approaches to forming predictions. Czasonis, Kritzman, and Turkington lay out the foundations of their cutting-edge approach to observing information from data. And then characterize patterns between multiple attributes, soon introducing the key concept of relevance. They then show how to use relevance to form predictions, discussing how to measure confidence in predictions by considering the tradeoff between relevance and noise. Prediction Revisited applies this new perspective to evaluate the efficacy of prediction models across many fields and preview the extension of the authors' new statistical approach to machine learning. Along the way they provide colorful biographical sketches of some of the key scientists throughout history who established the theoretical foundation that underpins the authors' notion of relevance--and its importance to prediction. In each chapter, material is presented conceptually, leaning heavily on intuition, and highlighting the key takeaways reframe prediction conceptually. They back it up mathematically and introduce an empirical application of the key concepts to understand. (If you are strongly disinclined toward mathematics, you can pass by the math and concentrate only on the prose, which is sufficient to convey the key concepts of this book.) In fact, you can think of this book as two books: one written in the language of poets and one written in the language of mathematics. Some readers may view the book's key insight about relevance skeptically, because it calls into question notions about statistical analysis that are deeply entrenched in beliefs from earlier training. The authors welcome a groundswell of debate and advancement of thought about prediction."-- Provided by publisher

Contents:

Cover

Title Page

Copyright

Contents

Timeline of Innovations

Essential Concepts

Preface

1 Introduction

Relevance

Informativeness

Similarity

Roadmap

2 Observing Information

Observing Information Conceptually

Central Tendency

Spread

Information Theory

The Strong Pull of Normality

A Constant of Convenience

Key Takeaways

Observing Information Mathematically

Average

Information Distance

Observing Information Applied

Appendix 2.1: On the Inflection Point of the Normal Distribution

References

3 Co‐occurrence

Co‐occurrence Conceptually

Correlation as an Information‐Weighted Average of Co‐occurrence

Pairs of Pairs

Across Many Attributes

Co‐occurrence Mathematically

The Covariance Matrix

Co‐occurrence Applied

4 Relevance

Relevance Conceptually

Relevance and Prediction

How Much Have You Regressed?

Partial Sample Regression

Asymmetry

Sensitivity

Memory and Bias

Relevance Mathematically

Prediction

Equivalence to Linear Regression

Relevance Applied

Appendix 4.1: Predicting Binary Outcomes

Predicting Binary Outcomes Conceptually

Predicting Binary Outcomes Mathematically

5 Fit

Fit Conceptually

Failing Gracefully

Why Fit Varies

Avoiding Bias

Precision

Focus

Fit Mathematically

Components of Fit

Fit Applied

6 Reliability

Reliability Conceptually

Reliability Mathematically

Reliability Applied

7 Toward Complexity

Toward Complexity Conceptually

Learning by Example

Expanding on Relevance

Toward Complexity Mathematically

Complexity Applied.

References

8 Foundations of Relevance

Observations and Relevance: A Brief Review of the Main Insights

Co‐occurrence

Fit and Reliability

Partial Sample Regression and Machine Learning Algorithms

Abraham de Moivre (1667-1754)

Pierre‐Simon Laplace (1749-1827)

Carl Friedrich Gauss (1777-1853)

Francis Galton (1822-1911)

Karl Pearson (1857-1936)

Ronald Fisher (1890-1962)

Prasanta Chandra Mahalanobis (1893-1972)

Claude Shannon (1916-2001)

Concluding Thoughts

Perspective

Insights

Prescriptions

Index

EULA.

Notes:

Includes index.

Description based on print version record.

Other Format:

Print version: Kritzman, Mark P. Prediction Revisited

ISBN:

9781119895596

1119895596

9781119895602

111989560X

OCLC:

1320819991