About this Book

Unlock the power of Python to master the world of quantitative finance! Whether you're an aspiring quant developer, an independent trader, or a seasoned programmer looking to transition into finance, this comprehensive guide has everything you need to build sophisticated financial applications.

Practical Quantitative Finance with Python delivers a hands-on approach to mastering modern financial modeling, quantitative analysis, and trading strategy development using Python's most powerful libraries, including NumPy, Pandas, SciPy, and cutting-edge machine learning tools.

This book is perfect for:

• Quant developers and analysts aiming to enhance their technical skills.
• Independent traders looking to build automated trading systems.
• Python programmers seeking to enter the lucrative field of quantitative finance.
• Students and professionals from math, physics, or engineering backgrounds eager to learn financial application development.

Inside, you’ll discover:

• A complete, step-by-step guide to building financial applications using Python.
• Real-world examples and reusable Python libraries for market data APIs, data visualization, option pricing, fixed-income instruments, machine learning, and trading strategies.
• Practical techniques to convert trading ideas into actionable strategies.
• In-depth explanations that cater to all experience levels, from beginners to advanced users.

Written by an industry expert, this book demystifies complex quantitative finance concepts and equips you with the skills to develop powerful business applications. Whether you're building pricing engines, algorithmic trading models, or financial data analytics tools, Practical Quantitative Finance with Python is your essential guide to success.

Start your journey today and transform your financial ideas into real-world applications!

Table of Contents

Contents	v
Introduction	1
Overview	1
What this Book Includes	2
Is this Book for You?	3
How this Book Is Organized	3
Use Code Examples	5
Customer Support	5
1	Setting Up Development Tools	7
1.1	Install Python	7
1.2	Install Visual Studio Code	10
1.3	Run Python Applications	10
1.4	Python Basics	12
1.4.1	Data Types	13
1.4.2	Functions	15
1.4.3	Control Flows	17
1.4.4	NumPy	20
1.4.5	Enums	23
1.4.6	Series	23
1.4.7	DataFrames	25
2	Database	27
2.1	Python Database API	27
2.2	Database Creation	29
2.2.1	Create Database Tables	29
2.2.2	Check Database	31
2.3	Seed Data	32
2.3.1	Helper Functions	32
2.3.2	Seed Data for Symbol	33
2.3.3	Seed Data for Price	34
2.3.4	Seed Data for IndexData	35
2.4	CRUD Operations	36
2.4.1	PyQt5 GUI	36
2.4.2	Insert Operation	39
2.4.3	Read Operation	42
2.4.4	Update and Delete Operations	45
3	Market Data	51
3.1	Market Data from Yahoo Finance	51
3.1.1	Market Data	52
3.1.2	Download Market Data	53
3.1.3	Save Market Data to Database	58
3.1.4	Stock Quote	65
3.2	Market Data from Alpaca	68
3.2.1	Client Classes	70
3.2.2	Stock Data	71
3.2.3	Intraday Stock Data	75
3.2.4	Data Streaming	78
3.3	Market Data from Charles Schwab	81
3.3.1	Initialize API	81
3.3.2	Stock Data	86
3.3.3	Intraday Stock Data	90
3.3.4	Data Streaming	92
3.4	ISDA Rates from IHS Markit	98
4	Data Visualization	105
4.1	Line Charts	105
4.1.1	Simple Line Charts	105
4.1.2	Multiple-Line Charts	109
4.1.3	Line Charts with Two Y-Axes	111
4.2	Specialized 2D Charts	114
4.2.1	Area Charts	114
4.2.2	Multiple-Area Charts	115
4.2.3	Bar Charts	117
4.2.4	Pie Charts	123
4.2.5	Polar Charts	126
4.3	3D Charts	130
4.3.1	3D Line Charts	130
4.3.2	3D Surface Charts	132
4.4	Stock Charts	140
4.4.1	Candlestick Charts	140
4.4.2	Candlestick and Volume Charts	143
4.4.3	Candlestick with Category	147
5	Linear Analysis	151
5.1	Simple Linear Regression	151
5.1.1	Implementation	152
5.1.2	R-Squared	153
5.1.3	What are Alpha and Beta?	154
5.1.4	SLR for Index Data	154
5.1.5	Data Splitting	158
5.1.6	SLR with Data Splitting for Index Data	160
5.1.7	SLR Results for Stocks	165
5.2	Simple 2D PCA	172
5.2.1	Implementation	172
5.2.2	PCA for Index Data	174
5.2.3	PCA for Stocks	178
5.2.4	Compare SLR and 2D PCA	182
5.3	Multiple Linear Regressions	184
5.3.1	Implementation	184
5.3.2	MLR for Index Data	186
5.3.3	MLR Results for Stocks	190
5.4	Multiple PCA	192
5.4.1	Implementation	192
5.4.2	MPCA for Index Data	195
5.4.3	MPCA Results for Stocks	198
6	Technical Indicators	203
6.1	Overlap Indicators	203
6.1.1	Install TA-Lib	204
6.1.2	Implementation	204
6.1.3	Moving Average Based Indicators	208
6.1.4	Bollinger Band Indicator	211
6.1.5	SAR Indicator	213
6.2	Momentum Indicators	214
6.2.1	Implementation	215
6.2.2	ADX Indicator	220
6.2.3	APO Indicator	221
6.2.4	Aroon Indicator	223
6.2.5	BOP Indicator	225
6.2.6	CCI Indicator	226
6.2.7	MACD Indicator	228
6.2.8	RSI Indicator	229
6.2.9	Stochastic Indicator	231
6.2.10	Williams %R Indicator	233
6.3	Volume Indicators	234
6.3.1	AD Indicator	234
6.3.2	OBV Indicator	236
6.4	Volatility Indicators	237
6.4.1	TR Indicator	237
6.4.2	ATR Indictor	238
6.4.3	NATR Indicator	239
7	Machine Learning	243
7.1	Data Preparation	243
7.1.1	Implementation	244
7.1.2	Check ML Data	247
7.2	Classification	251
7.2.1	Implementation	251
7.2.2	Decision Tree Classifier	256
7.2.3	Confusion Matrix	258
7.2.4	Random Forest Classifier	259
7.2.5	Extra Trees Classifier	260
7.2.6	KNN Classification	262
7.2.7	SVM Classifier	263
7.2.8	Gradient Boosting Classifier	265
7.3	Regression	267
7.3.1	Implementation	267
7.3.2	Decision Tree Regressor	273
7.3.3	AdaBoost Regressor	275
7.3.4	Random Forest Regressor	276
7.3.5	Limitation	278
7.4	Neural Networks	279
7.4.1	Introduction to Neural Networks	279
7.4.2	Data Normalization	282
7.4.3	Neural Networks for Classification	283
7.4.4	Neural Networks for Regression	289
8	Option Pricing	299
8.1	Introduction to Options	299
8.1.1	Option Payoffs	300
8.1.2	Option Value	300
8.2	Pricing European Options	301
8.2.1	Black-Scholes Model	301
8.2.2	Generalized Black-Scholes Model	302
8.2.3	Implementation	302
8.2.4	Black-Scholes Greeks	304
8.2.5	Results for Price and Greeks	310
8.2.6	Results for Implied Volatility	319
8.3	Pricing American Options	325
8.3.1	BAW Approximation	325
8.3.2	Implementation	326
8.3.3	BAW Results	330
8.4	Pricing Barrier Options	335
8.4.1	Standard Barrier Options Formulas	335
8.4.2	Implementation	337
8.4.3	Barrier Option Results	342
9	Option Pricing Using QuantLib	349
9.1	Introduction to QuantLib	349
9.1.1	Dates, Calendars, and Day Counters	349
9.1.2	Term Structures	351
9.2	European Options	352
9.2.1	Helper Functions	353
9.2.2	Price and Greeks Results	356
9.2.3	Helper Functions for Implied Volatility	362
9.2.4	Implied Volatility Results	364
9.3	American Options	368
9.3.1	Helper Functions	368
9.3.2	American Option Results	372
9.4	Barrier Options	377
9.4.1	Helper Functions	377
9.4.2	Barrier Option Results	378
9.5	Bermudan Options	384
9.5.1	Helper Functions	384
9.5.2	Bermudan Option Results	386
9.6	American Options in Real-World	391
9.6.1	Term Structure for Interest Rates	392
9.6.2	Dividend Yield Curve	394
9.6.3	Volatility Smile	395
9.6.4	Helper Functions	396
9.6.5	Real-World Option Results	398
10	Pricing Fixed-Income Instruments	403
10.1	Pricing Simple Bonds	403
10.1.1	Discounting Factors	404
10.1.2	Pricing Bonds with Flat Rates	405
10.1.3	Simple Bond Results	408
10.1.4	Compounding Frequency Conventions	411
10.1.5	Pricing Bonds with a Rate Curve	412
10.1.6	Yield To Maturity	416
10.2	Zero-Coupon Yield Curve	416
10.2.1	Treasury Zero-Coupon Yield Curve	417
10.2.2	Interbank Zero-Coupon Yield Curve	427
10.2.3	Credit Spread Term Structures	432
10.3	Bonds with Embedded Options	441
10.3.1	Callable Bonds	441
10.3.2	Convertible Bonds	445
10.4	CDS Pricing	451
10.4.1	Hazard Rate and Default Probability	451
10.4.2	Risky Annuities and Risky Durations	458
10.4.3	CDS Present Values	458
10.4.4	CDS Prices	467
11	Trading Strategies and Backtesting	475
11.1	Trading Strategy Identification	476
11.2	Get Started with Backtrader	478
11.2.1	Initialize Cerebro Engine	478
11.2.2	Add Market Data	479
11.2.3	Create Strategy	481
11.2.4	Strategy Performance	484
11.2.5	Order Size	486
11.3	Crossover Strategies	487
11.3.1	Two-SMA Crossover	487
11.3.2	Long-Only Strategy	488
11.3.3	Risk Measure	491
11.3.4	Short Only Strategy	495
11.3.5	With Additional Indicators	497
11.4	Z-Score Strategies	501
11.4.1	MA-Based Z-Scores	502
11.4.2	RSI-Based Z-Scores	507
11.4.3	PPO-Based Z-Score	509
11.5	Strategy Optimization	513
11.5.1	Crossover Strategy Optimization	514
11.5.2	Z-score Strategy Optimization	517
11.6	Stock Screener	519
Index	523

Introduction

        Overview
        What This Book Includes
        Is This Book for You
        How This Book is Organized
        Using Code Examples

---

Overview

Welcome to Practical Quantitative Finance with Python! This book provides all the tools you need to develop modern financial applications using Python. I hope it will prove useful for quant developers, quant analysts, individual traders, Python programmers, and students of all skill levels.

In recent years, quantitative finance has become an attractive field due to its intellectual challenges and high remuneration. Many scientists, engineers, and students aspire to transition into careers as quant developers or analysts in investment banks or hedge funds. Most of these individuals have strong backgrounds in mathematics, statistical analysis, physics modeling, and programming but lack the knowledge and experience specific to quantitative finance. A common question they ask is, “What do I need to prepare myself to become a quant developer or analyst?” This book aims to answer this question, equipping you with solid technical skills in quantitative analysis and development.

On the other hand, especially in the aftermath of the COVID-19 pandemic, more individuals are pursuing careers as independent (“retail”) quantitative traders, seeking to start their own quantitative or algorithmic trading businesses. This path offers the flexibility of working from home and setting your own hours. However, the most frequent question these individuals face is, “What kind of background do I need to be successful in quantitative trading?” Many of these aspiring traders have advanced degrees in physics, math, engineering, or computer science. Such training provides an edge in quantitative analysis and pricing complex derivative instruments. Yet, the ability to convert trading ideas into actionable strategies and the programming skills required to implement an automated trading system are equally vital. This book will provide you with the necessary analytical and programming techniques to succeed as an individual quantitative trader.

So, which programming language is most commonly used in quantitative finance? Traditionally, C++ has been the go-to language for pricing complex derivative securities, and much of the older financial infrastructure is built on it. However, Python has surged in popularity in quantitative finance, thanks to its ease of use, powerful tools, and vibrant community.

Python offers extensive libraries for numerical and science computing. For instance, NumPy provides powerful array and matrix operations, essential for numerical computations in finance; Pandas offers data structures like DataFrames for efficient data manipulation and analysis, which are crucial for working with financial time series data; and SciPy contains a wide range of scientific computing tools, including optimization, integration, and statistical functions used in financial modeling.

Additionally, Python dominates the machine learning space with libraries like scikit-learn, TensorFlow, and PyTorch, which are increasingly applied in finance for tasks such as algorithmic trading, risk management, and fraud detection.

Python’s clear and concise syntax makes it relatively easy to learn and use, even for those with limited programming experience. This reduces development time and allows quants to rapidly prototype and test models. Moreover, Python’s massive and active community provides ample resources, tutorials, and support, making it easier to find solutions and learn from others.

In summary, Python’s combination of powerful libraries, ease of use, strong community support, and versatility makes it an ideal language for quantitative finance. It enables quants to efficiently develop, test, and deploy complex financial models and applications. Therefore, this book will use Python as the programming language to develop various applications for financial markets.

I wrote this book with the intention of providing a complete and comprehensive explanation of modern application development in quantitative finance using Python. This book places special emphasis on creating various business applications and reusable Python libraries that can be directly applied in real-world finance scenarios. Much of the content is based on my own programming experience developing business applications for quantitative analysis in the financial industry.

Practical Quantitative Finance with Python equips you with everything you need to create your own advanced applications in quantitative finance and reusable packages using Python. It demonstrates how Python can be used to build a wide range of financial applications, from simple databases and market data APIs to data visualization, quantitative analysis, equity option pricing, complex fixed-income instruments, machine learning, and trading strategy development.

I will do my best to introduce you to modern application development in quantitative finance in a straightforward manner—simple enough to be easily followed by a quant or Python programmer with basic prior experience in developing business applications in finance.

What This Book Includes

This book and its sample code listings, which are available for download at my website at https://drxudotnet.com, provide you with

• A complete, in-depth instruction to modern web application development in quantitative finance with Python. After reading this book and running the example programs, you will be able to create various sophisticated business applications in quantitative finance using Python.
• Ready-to-run example programs that allow you to explore the quantitative finance programming techniques and understand how the algorithms work. You can modify the code examples or add new features to them to form the basis of your own projects. Some of the example code listings provided in this book are already sophisticated programming packages in quantitative finance that you can use directly in your own real-world business applications.
• Many classes and functions in the sample code listings that you will find useful in your quant development. These classes and functions include charting libraries, various quantitative analysis models, pricing engines for options and fixed income instruments, machine learning for trading strategy development and back-testing, and the other useful utility classes. You can extract these classes and functions and plug them into your own business applications.

Is This Book for You

You do not need to be an experienced quant developer/analyst or Python developer to use this book. I designed it to be useful to people of all levels of Python programming experience and financial backgrounds. In fact, if you have some prior experience with quantitative analysis/development and programming languages such as C++, Java, R, Python, VBA, C#, or JavaScript, you will be able to sit down at your computer, start Visual Studio Code, follow the examples provided in this book, and quickly become proficient in quantitative application development.

For those of you who are already experienced quant analysts/developers or Python programmers, I believe this book has much to offer as well. A great deal of the information in this book about Python programming in quantitative finance is not available in other tutorials and reference books. Additionally, you can use most of the example programs in this book directly in your own real-world application development. This book will provide you with a level of detail, explanation, instruction, and sample code that will enable you to do just about anything related to quantitative finance application development using Python.

Quant analysts/developers, individual quant traders, and Python programmers can routinely use the majority of the example programs in this book. Throughout, I emphasize the usefulness of the application development for real-world quantitative finance problems. If you follow the instructions in this book closely, you will be able to develop various practical business applications in quantitative finance, from linear analysis and machine learning to pricing engines and trading strategy development.

At the same time, I will not spend too much time discussing programming style, execution speed, and code optimization, as many books already cover these topics extensively. Most of the example programs in this book omit error handling to make the code easier to understand by focusing solely on key concepts and practical applications.

How This Book Is Organized

This book is structured into eleven chapters, each exploring a distinct topic related to quantitative finance applications using Python. Below is a summary of each chapter to provide an overview of the book’s contents:

Chapter 1, Setting up Development Tools
This chapter covers the basics of Python, including how to set up the tools, packages, and development environment required for building a Python application with the Visual Studio Code IDE.

Chapter 2, Database
This chapter introduces SQLite and Python database API. It demonstrates how to create simple database and how to interact with the data in Python applications through data services.

Chapter 3, Market Data
This chapter explains how to interact with market data providers’ API and retrieve free market data from online sources. This includes end of the day (EOD) stock data, intraday data, real-time stock price quotes, and interest rate data.

Chapter 4, Data Visualization
Data visualization plays a critical role in quantitative finance and trading. Quant analysts and traders need to visually monitor real-time changes in the market and trading signals on their screens. This chapter illustrates how to use the Plotly library to create various charts and display the market data in a Blazor application.

Chapter 5, Linear Analysis
This chapter presents fundamental analysis approaches in quantitative finance based on linear analysis. It covers how to develop various business applications using linear regression, principal component analysis (PCA), and correlation.

Chapter 6, Technical Indicators
This chapter discusses various technical indicators commonly used in quantitative analysis. A technical indicator is a mathematical calculation based on historic market data, used to predict market direction. I will show you how to convert various indicators provided in TA-Lib library into data services and how to apply them to your Python applications.

Chapter 7, Machine Learning
This chapter covers the advanced quantitative analysis techniques, specifically machine learning. Machine-learning technique has become one of the most promising fields in quantitative finance, widely used in predicting future stock prices. This chapter will focus on supervised learning and present several commonly used machine-learning algorithms in finance, including decision trees, K-nearest neighbors, support vector machines, and neural networks.

Chapter 8, Option Pricing
This chapter discusses the Black-Scholes formula used for options pricing. It presents several different implementations for calculating the price and Greeks of European and American options, as well as barrier options. You will gain a better understanding of how the algorithm works in pricing options through coding exercises.

Chapter 9, Option Pricing Using QuantLib
This chapter demonstrates how to use the open-source library QuantLib to calculate the price and Greeks of European and American options. It also discusses how to use this library to price other options, including barrier options, Bermudan options, and real-world options.

Chapter 10, Pricing Fixed-Income Instruments
This chapter demonstrates how to price fixed-income instruments, including interest rates, bonds, and credit default swaps. It also covers related topics such as cash flows, term structures, yield curves, discount factors, and zero-coupon bonds. Detailed procedures are provided on how to use the QuantLib library to price these complex financial instruments.

Chapter 11, Trading Strategies and Backtesting
This chapter presents several trading strategies using simple quantitative analysis techniques, including crossovers and z-score based on commonly used technical indicators. It also covers a how to use the Backtrader framework to backtest the historical performance of your strategies in stock trading.

Using Code Examples

You may use the code in this book in your own applications and documentation without needing to contact the author for permission, unless you are reproducing a significant portion of the code. For instance, writing a program that utilizes several code segments from this book does not necessitate permission. However, selling or distributing the example code listings requires permission. If you plan to integrate a substantial amount of example code from this book into your applications and documentation, you will also need permission. Integrating the example code from this book into commercial products is prohibited without written permission from the author.