Book Image

Python for Finance Cookbook - Second Edition

By : Eryk Lewinson

5 (1)

Book Image

Python for Finance Cookbook - Second Edition

5 (1)

By: Eryk Lewinson

Overview of this book

Python is one of the most popular programming languages in the financial industry, with a huge collection of accompanying libraries. In this new edition of the Python for Finance Cookbook, you will explore classical quantitative finance approaches to data modeling, such as GARCH, CAPM, factor models, as well as modern machine learning and deep learning solutions. You will use popular Python libraries that, in a few lines of code, provide the means to quickly process, analyze, and draw conclusions from financial data. In this new edition, more emphasis was put on exploratory data analysis to help you visualize and better understand financial data. While doing so, you will also learn how to use Streamlit to create elegant, interactive web applications to present the results of technical analyses. Using the recipes in this book, you will become proficient in financial data analysis, be it for personal or professional projects. You will also understand which potential issues to expect with such analyses and, more importantly, how to overcome them.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Acquiring Financial Data

Acquiring Financial Data

Getting data from Yahoo Finance

Getting data from Nasdaq Data Link

Getting data from Intrinio

Getting data from Alpha Vantage

Getting data from CoinGecko

Data Preprocessing

Data Preprocessing

Converting prices to returns

Adjusting the returns for inflation

Changing the frequency of time series data

Different ways of imputing missing data

Converting currencies

Different ways of aggregating trade data

Visualizing Financial Time Series

Visualizing Financial Time Series

Basic visualization of time series data

Visualizing seasonal patterns

Creating interactive visualizations

Creating a candlestick chart

Exploring Financial Time Series Data

Exploring Financial Time Series Data

Outlier detection using rolling statistics

Outlier detection with the Hampel filter

Detecting changepoints in time series

Detecting trends in time series

Detecting patterns in a time series using the Hurst exponent

Investigating stylized facts of asset returns

Technical Analysis and Building Interactive Dashboards

Technical Analysis and Building Interactive Dashboards

Calculating the most popular technical indicators

Downloading the technical indicators

Recognizing candlestick patterns

Building an interactive web app for technical analysis using Streamlit

Deploying the technical analysis app

Time Series Analysis and Forecasting

Time Series Analysis and Forecasting

Time series decomposition

Testing for stationarity in time series

Correcting for stationarity in time series

Modeling time series with exponential smoothing methods

Modeling time series with ARIMA class models

Finding the best-fitting ARIMA model with auto-ARIMA

Machine Learning-Based Approaches to Time Series Forecasting

Machine Learning-Based Approaches to Time Series Forecasting

Validation methods for time series

Feature engineering for time series

Time series forecasting as reduced regression

Forecasting with Meta’s Prophet

AutoML for time series forecasting with PyCaret

Multi-Factor Models

Multi-Factor Models

Estimating the CAPM

Estimating the Fama-French three-factor model

Estimating the rolling three-factor model on a portfolio of assets

Estimating the four- and five-factor models

Estimating cross-sectional factor models using the Fama-MacBeth regression

Modeling Volatility with GARCH Class Models

Modeling Volatility with GARCH Class Models

Modeling stock returns’ volatility with ARCH models

Modeling stock returns’ volatility with GARCH models

Forecasting volatility using GARCH models

Multivariate volatility forecasting with the CCC-GARCH model

Forecasting the conditional covariance matrix using DCC-GARCH

Monte Carlo Simulations in Finance

Monte Carlo Simulations in Finance

Simulating stock price dynamics using a geometric Brownian motion

Pricing European options using simulations

Pricing American options with Least Squares Monte Carlo

Pricing American options using QuantLib

Pricing barrier options

Estimating Value-at-Risk using Monte Carlo

Asset Allocation

Asset Allocation

Evaluating an equally-weighted portfolio’s performance

Finding the efficient frontier using Monte Carlo simulations

Finding the efficient frontier using optimization with SciPy

Finding the efficient frontier using convex optimization with CVXPY

Finding the optimal portfolio with Hierarchical Risk Parity

Backtesting Trading Strategies

Backtesting Trading Strategies

Vectorized backtesting with pandas

Event-driven backtesting with backtrader

Backtesting a long/short strategy based on the RSI

Backtesting a buy/sell strategy based on Bollinger bands

Backtesting a moving average crossover strategy using crypto data

Backtesting a mean-variance portfolio optimization

Applied Machine Learning: Identifying Credit Default

Applied Machine Learning: Identifying Credit Default

Loading data and managing data types

Exploratory data analysis

Splitting data into training and test sets

Identifying and dealing with missing values

Encoding categorical variables

Fitting a decision tree classifier

Organizing the project with pipelines

Tuning hyperparameters using grid searches and cross-validation

Advanced Concepts for Machine Learning Projects

Advanced Concepts for Machine Learning Projects

Exploring ensemble classifiers

Exploring alternative approaches to encoding categorical features

Investigating different approaches to handling imbalanced data

Leveraging the wisdom of the crowds with stacked ensembles

Bayesian hyperparameter optimization

Investigating feature importance

Exploring feature selection techniques

Exploring explainable AI techniques

Deep Learning in Finance

Deep Learning in Finance

Exploring fastai’s Tabular Learner

Exploring Google’s TabNet

Time series forecasting with Amazon’s DeepAR

Time series forecasting with NeuralProphet

Other Books You May Enjoy

Other Books You May Enjoy

Index

Customer Reviews

5 (1)

5 star

100%

4 star

0

3 star

0

2 star

0

1 star

0

Backtesting a buy/sell strategy based on Bollinger bands

Bollinger bands are a statistical method, used for deriving information about the prices and volatility of a certain asset over time. To obtain the Bollinger bands, we need to calculate the moving average and standard deviation of the time series (prices), using a specified window (typically 20 days). Then, we set the upper/lower bands at K times (typically 2) the moving standard deviation above/below the moving average.

The interpretation of the bands is quite simple: the bands widen with an increase in volatility and contract with a decrease in volatility.

In this recipe, we build a simple trading strategy that uses Bollinger bands to identify underbought and oversold levels and then trade based on those areas. The rules of the strategy are as follows:

Buy when the price crosses the lower Bollinger band upward.
Sell (only if stocks are in possession) when the price crosses the upper Bollinger band...