Demo and overview of IMDB Film and TV ratings prediction system using data mining and machine learning techniques. This is a tool that film, tv, and video game production companies can use to determine the ratings of a proposed future film, TV show, or video game before they green-light a proposed project and lock a cast and crew. Our regression method, which produces a predicted score, yielded the highest accuracy in our results with a 95.5% accuracy rate on the top titles we tested it with from a test period of data in late 2018. We loaded IMDB's entire film and TV history since the invention of film (earliest entry was 1894) into a PHP web application and MySQL database. Included in this data is all user ratings of said film and tv shows on a (1-10) scale. We used Classification to label potential new projects: Excellent (7.5 rating and above), Average (5 - 7.4), Poor (2.5 - 4.9), and Terrible (less than 2.5). We used Clustering to analyze the data and identify trends in the data historically and Anomaly Detection to identify Outliers in the data. Further testing on future titles should done to get a true accuracy rate on each function. Our test data consisted of all data provided from IMDB up to late August 2018. We loaded that data up then to create a point where we could test our predictions against the actual ratings titles received which were released between this time and our final report in December 2018.