Customer Behavior & Trending Analysis

  • Tech Stack: Pyspark, SparkSQL, MySQL, Jupyter Notebook, PowerBI
  • Github URL: Project Link |

Sumary: Analyze customer's television usage behavior data to track customer's trending preferences, thereby building CRM Analytics and Customer360 models.

  • Collect, preprocess data from data sources using mysql, pyspark.
  • Using Pyspark to Data cleaning, Performing Extract , Transform and Load ( ETL) data from data sources then put into data warehouse.
  • Using SQL to query from data warehouse and process data for Analytics & reports to extract insights.
  • Performing Data Visualizing and Diagnostic Data Analytics with PowerBI.
  • Optimize query to build predictive models using Machine Learning algorithms and Statistics