1. Introduction to Finance Analytics

1.1 Analytics in Finance

1.2 Data-Driven Finance

1.3 Organization of the Book

1.4 Use of R and Python

1.5 What this Book is Not About

1.6 Data and Codes Used in this Book

1.7 Skills and Resources Needed to Excel in Finance Analytics

2. Data in Finance

2.1 Introduction

2.2 Fundamental Data

2.3 Obtaining Fundamental Data

2.4 Marker Data

2.5 Analysts’ Data

2.6 Alternate Data

2.7 Downloading Data Using an API

3. Wrangling Financial Data

3.1 Reading Financial Data

3.2 Check Data Types (Variable Types)

3.3 Clean Variable Names

3.4 Managing Missing Data

3.5 Managing Invalid Data

3.6 Managing Outliers

3.7 Long and Wide Form Data

4. Exploratory Analysis of Financial Data

4.1 Introduction

4.2 Univariate Analysis of Fundamental Data

4.3 Bi-variate and Multi-variate Analysis of Fundamental Data

4.4 Analysis of Time Series Data

5. Understanding Basic Finance using R and Python

5.1 Introduction

5.2 Time Value of Money

5.3 Risk and Return

5.4 Asset Valuation

6. Accounting Data Analytics

6.1 Introduction

6.2 Case 1: Detecting Patterns in Financial Statements

6.3 Case 2: Predicting Corporate Bankruptcy

7. Applications of Natural Language Processing in Finance

7.1 Sourcing Text Data

7.2 Text Preprocessing

7.3 Case 1: Summarizing a Document

7.4 Case 2: Sentiment Analysis

7.5 Case 3: Sentiment Analysis Using Machine Learning

8. Financial Fraud Analytics

8.1 Benford’s Law

8.2 Predicting Credit Card Frauds

9. Valuation Analytics

9.1 Introduction

9.2 Theory of Valuation

9.3 Building a Valuation Model

9.4 Creating a Valuation Function

9.5 Estimating Implied Returns

9.6 Extension of the Model

9.7 Building the Valuation Function in Python

9.8 Valuation of Walmart Inc.

10. Portfolio Analytics

10.1 Introduction

10.2 Return and Risk of a Portfolio

10.3 Markowitz Optimization Process

10.4 Portfolio Optimization using Python

10.5 Portfolio Performance Evaluation

10.6 Portfolio Insurance

11. Developing and Backtesting Technical Trading Rules

11.1 Trend Indicators

11.2 Momentum Indicators

11.3 Volatility Indicators

11.4 Volume Indicators

11.5 Backtesting

11.6 Technical Analysis in Python

11.7 Comparing 5-day EMA with 21-day EMA in Python

11.8 Quantstrat to Automate Backtesting

12. Predicting Stock Prices/Returns

12.1 Predicting Stock Returns Based on Accounting Ratios

12.2 Predicting Stock Returns (Prices) using Past Stock Returns (Prices) Data

12.3 Predicting Stock Prices using Technical Indicators

12.4 Predicting Stock Returns using Valuation Multipliers and Value Drivers

12.5 Predicting Returns Based on Factor Exposures/Stock Characteristics

Appendix 1: Installing R and Python

Appendix 2: Introduction to R

Appendix 3: Introduction to Python

Appendix 4: A Concise Introduction to Machine Learning

Index

Financial Analytics applies modern data science tools to explore and understand interesting financial data patterns. Though the use of quantitative tools is nothing new in finance, modern financial analytics is different due to three recent trends: i) improved computing power with the availability of GPUs and TPUs, ii) advanced ML and AI algorithms, and iii) access to large volumes of practically all types of data. The new-age Financial Analytics takes a data-driven approach to study finance. Instead of making assumptions about the distribution of data or the relationship between variables, it simply lets the data speak for itself.