Hands-On Machine Learning for Algorithmic Trading

Multinomial Naive Bayes model

Next, we train a Naive Bayes classifier using a document-term matrix produced by CountVectorizer with default settings:

nb = MultinomialNB()nb.fit(train_dtm,train.stars)predicted_stars = nb.predict(test_dtm)

The prediction produces 64.7% accuracy on the test set, a 24.4% improvement over the benchmark:

accuracy_score(test.stars, predicted_stars)0.6465164206691094