SharkTank Deal Prediction: Dataset and Computational Model

Abstract

SharkTank is a television show where start-ups pitch their idea to a panel of five investors (sharks) in hopes of striking a deal in the form of equity or royalties for money and other business perks. Since its inception, SharkTank has been a center of discussion and analysis for fans, statisticians, and business people alike in hopes of cracking the code to the start-up world and figuring out the formula for the next big ‘thing’. Most of these discussions and analyses have come in the form of blogs, articles, and academic research. However, there has been a lack of complete datasets and application of computational models for further analysis. In this paper, we investigate factors that play into the SharkTank deal. To this end, we first collect a new dataset, SharkTank Deal Dataset (STDD), by combining data from multiple public sources. The dataset includes descriptive features of each start-up such as product category, team composition, valuation, equity offering, specific sharks that appear on that episode, and state origin. For the computational model, we propose a new computational model to predict whether a start-up strikes a deal with a shark. We conduct experiments to demonstrate the superiority of our model over the baselines.