Personalized Cancer Diagnosis - MultiClass classification Problem
Built a machine learning model to diagnose the cancer patient.
- Train multiple machine learning model i.e Naive Bayes, K-nearest Neighbors, Random Forest
and XGBoost algorithms.
- Found XGBoost - best performer model, used logloss, Precision and Recall as evaluation
metrics.
Taxi demand prediction in New York City - Time-Series Problem (Regression)
Used publicly available dataset from [NYC Yellow
Taxi](https://www1.nyc.gov/site/tlc/index.page)
- First Model used is the Moving Averages Model which uses the previous n values in order to
predict the next value
- Other models - Weighted Moving Averages, Exponential Weighted Moving Averages, EWMA -
perform well compared to others.
- Regression models - Linear Regression, Random Forest Regressor, XgBoost Regressor.
- XgBoost Regressor performs well in Regression models but there is slightly difference in
the MAPE value between EWMA and XgBoost.
- Learning - Simple model can perform well.
NLP Problem - Review Polarity classification of Amazon fine food reviews
Built multiple machine learning model to find best performer model.
- Used Feature Embedding methods - Bag of Words (BoW), TF-IDF vectorizer
- Found XGBoost - best performer model
- Evaluation Metrics - AUC and F1-score