/Machine-Learning-for-Finance

Machine Learning for Finance, published by Packt

Primary LanguageJupyter NotebookMIT LicenseMIT

$5 Tech Unlocked 2021!

The $5 campaign runs from December 15th 2020 to January 13th 2021.

Machine Learning for Finance

This is the code repository for Machine Learning for Finance, published by Packt. It contains all the supporting project files necessary to work through the book from start to finish.

About the book

Machine Learning for Finance explores new advances in machine learning and shows how they can be applied in the financial sector. It explains the concepts and algorithms behind the main machine learning techniques and provides example Python code for implementing the models yourself.

How to run this code

The code in this repository is quite compute heavy and best run on a GPU enabled machine. The datascience platform Kaggle offers free GPU recourses together with free online Jupyter notebooks. To make edits on the Kaggle notebooks, click 'Fork' to create a new copy of the notebook. You will need a Kaggle account for this.

Alternatively you can just view the notebooks on NB Viewer or download the code and run it locally.

Chapter 1 - A neural Network from Scratch

A neural network from Scratch & Intro to Keras: Run on Kaggle, View Online

Excercise excel sheet: Download

Chapter 2 - Structured Data

Credit card fraud detection: Run On Kaggle, View Online

Chapter 3 - Computer Vision Building Blocks

Classifying MNIST digits: Run On Kaggle, View Online

Chapter 4 - Practical Computer Vision

Classifying Plants: View Online, Run On Colab

Intro to Python Generators: Run On Kaggle

Keras Generator with Logistic Regression: Run On Kaggle

Stacking VGG: Run On Kaggle

Preprocessing and Saving VGG Outputs: Run On Kaggle

Rule Based Preprocessing and Augmentation: Run On Kaggle

Visualizing ConvNets: Run On Kaggle

Chapter 5 - Time Series

Forecasting Web Traffic: Classic Methods: Run On Kaggle, View Online

Forecasting Web Traffic: Time Series Neural Nets: Run On Kaggle, View Online

Expressing Uncertainty with Bayesian Deep Learning: Run On Kaggle, View Online

Chapter 6 - Natural Language processing

Analyzing the News: Run On Kaggle, View Online

Classifying Tweets: Run On Kaggle, View Online

Topic modeling with LDA: Run On Kaggle, View Online

Sequence to Sequence models: Run On Kaggle, View Online

Chapter 7 - Generative Models

(Variational) Autoencoder for MNIST: Run On Kaggle, View Online

(Variational) Autoencoder for Fraud Detection: Run On Kaggle, View Online

MNIST DCGAN: Run On Kaggle, View Online

Semi Supervised Generative Adversarial Network for Fraud Detection: Run On Kaggle, View Online

Chapter 8 - Reinforcement Learning

Q-Learning: View Online

A2C Pole Balancing: View Online

A2C for Trading: Run On Kaggle View Online

Chapter 9 - Debugging ML Systems

Unit Testing Data: Run On Kaggle, View Online

Hyperparameter Optimization: View Online

Learning Rate Search: View Online

Using Tensorboard: View Online

Converting Keras Models to TF Estimators: View Online

Faster Python with Cython: Download Part 1, Download Part 2

Chapter 10 - Fighting Bias in Machine Learning

Understanding Parity in Excel: Download

Learning How to Pivot: View Online

Interpretability with SHAP: View Online