Offer and Deal-Quality Prediction using Machine learning and Fuzzy approach: A Shark Tank India Case Study

The Hindi-language television program Shark Tank India, which airs on Sony LIV, has changed the conversation in many Indian homes and raised awareness of entrepreneurship and start-ups. Shark Tank India depicts the background of each start-up and the business owners pitching their wholesome ideas to a panel of Sharks (Investors) who are entrepreneurs in various industries. Sharks then opt to invest in exchange for equity in the company (some percentage of ownership). Two of the major problems faced by startups before coming on the show is an understanding of what role each business factor plays in determining the proposition of offer by the sharks and the quality of deal done with or without negotiation with the sharks. To address this issue, we created a new dataset for Shark Tank India that contains essential features representing information about participating startups. Then we used this data to propose two ambient systems. The first one uses machine learning to predict whether investors will make an offer to the pitching team, with the Artificial Neural Network (ANN) model performing best with an F1 score of 87.09%, and the second one uses a fuzzy system consisting of 22 rules to categorize the quality of a deal after an investment is made.