Machine Learning RUM - Velocity 2016
•Download as PPTX, PDF•
1 like•853 views
Presentation from Velocity 2016 on using Machine Learning to determine the metrics that drive bounce and conversions
Report
Share
More Related Content
Viewers also liked
Viewers also liked (15)
Similar to Machine Learning RUM - Velocity 2016
Similar to Machine Learning RUM - Velocity 2016 (20)
More from Patrick Meenan
More from Patrick Meenan (18)
Recently uploaded
Recently uploaded (20)
Machine Learning RUM - Velocity 2016
- 1. Using machine learning to determine drivers of bounce and conversion 2016 Velocity Santa Clara
- 3. What we did
- 6. Random Forest Lots of random decision trees
- 7. Vectorizing the data • Everything needs to be numeric • Strings converted to several inputs as yes/no (1/0) • i.e. Device Manufacturer – “Apple” would be a discrete input • Watch out for input explosion (UA String)
- 8. Balancing the data • 3% Conversion Rate • 97% Accurate by always guessing no • Subsample the data for 50/50 mix
- 9. Validation Data • Train on 80% of the data • Validate on 20% to prevent overfitting
- 10. Smoothing the data • ML works best on normally distributed data scaler = StandardScaler() x_train = scaler.fit_transform(x_train) x_val = scaler.transform(x_val)
- 11. Input/Output Relationships • SSL highly correlated with Conversions • Long sessions highly correlated with not bouncing • Remove correlated features from training
- 12. Training Deep Learning model = Sequential() model.add(...) model.compile(optimizer='adagrad', loss='binary_crossentropy', metrics=["accuracy"]) model.fit(x_train, y_train, nb_epoch=EPOCH_COUNT, batch_size=32, validation_data=(x_val, y_val), verbose=2, shuffle=True)
- 13. Training Random Forest clf = RandomForestClassifier(n_estimators=FOREST_SIZE, criterion='gini', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features='auto', max_leaf_nodes=None, bootstrap=True, oob_score=False, n_jobs=12, random_state=None, verbose=2, warm_start=False, class_weight=None) clf.fit(x_train, y_train)
- 15. What we learned
- 16. Takeaways
- 18. Thanks!