In this project we have developed Content based Recommendation Engine for S&P 500 Stocks using PySpark . The data has been gathered from Yfinance Python library, an API that scrapes and provides data for Yahoo Finance Website. This application can be scaled to other registered companies, along with incorporation of historical data. Using PySpark will enable the application to change recommendations in real-time with less refresh time exploiting Pysparks parallel processing/Distriburted computing.
Files Navigation-
Data Collection-
S&P_500_info_Datacollection.ipynb
S&P_500_recomm_Datacollection.ipynb
Data Visualkisation-
Data_Visualisations.ipynb
Data Pre-Processing and Model Building
Cosine_Similarity_Description.ipynb
PPT Presentation-
Stock Recommendation Engine Using PySpark (3).pptx
Data-
stocks_final_data.csv
Team Contact Sai Suraj Argula https://www.linkedin.com/in/suraj-argula/
Vinay Kumar Reddy https://www.linkedin.com/in/vinay-kumar-reddy-baradi/
Girija Bandaru https://www.linkedin.com/in/girija-bandaru-2687b994/
Anusha Seshagiri https://www.linkedin.com/in/anusha-seshagiri-071227105/