Pinned Loading

1. SparkML_on_AWS SparkML_on_AWS Public

   Utilizing AWS EMR and S3, leveraged Apache Spark to train numerous ML models in parallel to predict NYC taxi demand, 7 days ahead, for a given zone and hour of the day.

   HTML

2. HybridRecommenderSystem HybridRecommenderSystem Public

   This project develops a fast and accurate movie recommender system using a hybrid ML approach, user clustering, and categorical movie clustering.

   Jupyter Notebook

3. OutlierDetection OutlierDetection Public

   Mutual Information and reduced Spectral Clustering for outlier detection, compared against Isolation Forest and LOF

   Jupyter Notebook

4. RNN-Time-Series RNN-Time-Series Public

   A Recurrent Neural Network approach to forecasting a time series. The lookback window size, dropout rate, and recurrent dropout rate are used as hyperparameters for tuning.

   Jupyter Notebook

5. Imbalanced_Classification Imbalanced_Classification Public

   Classification on an imbalanced dataset, evaluating several model-resampling method combinations with hyperparameter tuning.

   Jupyter Notebook

6. SegmentedModelTraining SegmentedModelTraining Public

   A repository implementing feature-wise model segmentation using XGBoost, where separate models are trained for each unique value of a specified feature, enabling more targeted and accurate predicti…

   Jupyter Notebook