We use a simplified version of the data set constructed in Chapter 4, Alpha Factor Research. It consists of daily stock prices provided by Quandl for the 2010-2017 period and various engineered features. The details can be found in the data_prep notebook in the GitHub repo for this chapter. The decision tree models in this chapter are not equipped to handle missing or categorical variables, so we will apply dummy encoding to the latter after dropping any of the former.
- Title Page
- Copyright and Credits
- About Packt
- Contributors
- Preface
- Machine Learning for Trading
- How to read this book
- The rise of ML in the investment industry
- Design and execution of a trading strategy
- ML and algorithmic trading strategies
- Summary
- Market and Fundamental Data
- Alternative Data for Finance
- Alpha Factor Research
- Strategy Evaluation
- How to build and test a portfolio with zipline
- How to measure performance with pyfolio
- How to avoid the pitfalls of backtesting
- How to manage portfolio risk and return
- Summary
- The Machine Learning Process
- Learning from data
- The machine learning workflow
- Basic walkthrough – k-nearest neighbors
- Frame the problem – goals and metrics
- Collecting and preparing the data
- Explore, extract, and engineer features
- Selecting an ML algorithm
- Design and tune the model
- How to use cross-validation for model selection
- Parameter tuning with scikit-learn
- Challenges with cross-validation in finance
- Summary
- Linear Models
- Linear regression for inference and prediction
- The multiple linear regression model
- How to build a linear factor model
- Shrinkage methods: regularization for linear regression
- How to use linear regression to predict returns
- Linear classification
- Summary
- Time Series Models
- Analytical tools for diagnostics and feature extraction
- Univariate time series models
- Multivariate time series models
- Summary
- Bayesian Machine Learning
- How Bayesian machine learning works
- Probabilistic programming with PyMC3
- Summary
- Decision Trees and Random Forests
- Gradient Boosting Machines
- Unsupervised Learning
- Working with Text Data
- How to extract features from text data
- From text to tokens – the NLP pipeline
- From tokens to numbers – the document-term matrix
- Text classification and sentiment analysis
- Summary
- Topic Modeling
- Learning latent topics: goals and approaches
- Latent semantic indexing
- Probabilistic latent semantic analysis
- Latent Dirichlet allocation
- Summary
- Word Embeddings
- How word embeddings encode semantics
- Word vectors from SEC filings using gensim
- Sentiment analysis with Doc2vec
- Bonus – Word2vec for translation
- Summary
- Next Steps
- Key takeaways and lessons learned
- ML for trading in practice
- Conclusion
- Other Books You May Enjoy
How to prepare the data
-
No Comment
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.