Yelp Big Data Analytics

For my MIS elective course Big Data at San Jose State University, we gathered several gigabytes of json data from Yelp across many years. The accumulation of years of user reviews, business data, ratings, categories and so on forms an abundance of data, but without proper analysis, it cannot serve Yelp's business needs. As part of the public Yelp Dataset Challenge, we parsed and analyzed the data using Python PySpark and formed visualizations in Tableau to address Yelp's business questions regarding business hours posted and the annual reviews received. Our programming, findings, and BI recommendations to Yelp are encoded in the Jupyter Notebook.

As this course was during Spring 2020, we also had to adjust to the pandemic by adapting to remote collaboration and lectures.