Popular repositories Loading

1. immigration_data_etl_analysis immigration_data_etl_analysis Public

   This project demonstrates skills in data engineering, specifically it contains an efficient ETL process utilizing AWS EC2, EMR and S3, Python and Spark and orchestrating the data pipeline with Airflow

   Python 3 2

2. prod2vec prod2vec Public

   This project contains a pipeline, orchestrated with Airflow, for training product vectors (prod2vec) with Amazon Sagemaker

   Python 2 2

3. next-basket-prediction next-basket-prediction Public

   Utilizes sequence models to generate "next basket" recommendations for a grocery retail dataset

   Python 2 1

4. grocery-recommender grocery-recommender Public

   This project builds a hybrid recommender system for a grocery store utilizing Matrix Factorization and classification algorithms

   Jupyter Notebook 1

5. shopping-missions shopping-missions Public

   Creates "shopping missions", a segmentation of baskets where those baskets contain similar items. The segmentation is developed using principles from NLP, specifically topic models. The pipeline ut…

   Python

6. cust2vec cust2vec Public

   Generates customer vectors utilizing doc2vec models and creates customer segments by clustering customers with similar vectors

   Python 1