Arjun Kulothungun3 days ago
Data Science / Machine Learning Resources
I maintain this list of data science and machine learning resources for myself and for new entrants to the field. Feedback is appreciated.
Ground-level material:
- Data Science for Business : one of the few books that starts with business problems and shows how ML/DS can be applied. Good place to start in the field.
- Introduction to Information Retrieval : by Chris Manning et al. : blend of machine learning and software engineering to build info retrieval / search systems.
- fastml.com : blog covers explanations and attempts at a variety of machine learning models, good place for looking at a variety of ML ideas
- blog.echen.me : detailed exploration of specific data science problems / areas
- bayesian methods for hackers : groundwork for bayesian analysis
- primer on neural networks : by andrej karpathy
- NLP and neural networks : yoav goldberg
Various topics:
- Propensity modeling: http://blog.echen.me/2014/08/15/propensity-modeling-causal-inference-and-discovering-drivers-of-growth/
- A/B testing pitfalls: https://www.quora.com/When-should-A-B-testing-not-be-trusted-to-make-decisions
- Causal impact modeling: http://multithreaded.stitchfix.com/blog/2016/01/13/market-watch
Deeper material:
- Elements of Statistical Learning : Frequentist take on a variety of machine learning techniques, a good reference book
- Bayesian Data Analysis : first level bayesian analyses
- Linear Dynamic Systems : Video lectures by Steven Boyd on linear algebra, oriented around practical applications rather than heavy theory.
- Pattern Recognition and Machine Learning : Bayesian view of machine learning
- Recommendation Systems handbook : good intro and good reference too
Software Engineering materials:
Other materials:
- Stock compensation: https://blog.wealthfront.com/new-college-grad-stock-compensation/