School of Business and Management Department of Information Systems, Business Statistics and Operations Management 211 Applicability of Deep Learning Solutions to Business Problems Supervisor: KWOK James Sai Ho / ISOM Student: YEUNG Man Yin Michael / MAEC Course: UROP1000, Summer This paper investigates the selection of specifications of deep neural networks (DNNs) for binary classification in business problems, including input dataset dimensionality and model structure. In this study, specifications of DNN models designed for different business applications are used as the empirical data for analyses. These DNN models are tuned to have test accuracies optimized as possible by varying specifications. The results showed that the number of features, number of training samples and number of neurons are important factors having positive relationships with test accuracies. The relationships are modelled by an asymptotic regression model. The results provide a guideline for building DNN models for business binary classification problems and an estimator is proposed for the anticipation of the test accuracies of such models. Gender-Biased Perception Towards Entrepreneurship Supervisor: KWON Ohchan / ISOM Student: ARISTIA Joan / QFIN WONG Tsz Kwan / IS Course: UROP1000, Summer UROP1100, Summer In comparison to male entrepreneurs, the number of female entrepreneurs is far below. This indicates that there is a gender gap in entrepreneurship. In this research, we examine whether the gender gap is influenced by a gender-biased perception toward entrepreneurship. By collecting data from the American business reality television series, Shark Tank, we investigate if female entrepreneurs were particularly disadvantaged in getting investments from the investors. After the data collection process, the data is analyzed with R-programming language. The result of the analysis suggests that female entrepreneurs are at a disadvantage compared to male entrepreneurs. So the case of gender-biased perception toward entrepreneurship is apparent. This conclusion is derived from the value of the company and the number of bids received by female entrepreneurs which is less than male entrepreneurs. Gender-Biased Perception Towards Entrepreneurship Supervisor: KWON Ohchan / ISOM Student: QUACH Tuan Kiet / SBM TAN Chen-yi / SBM Course: UROP1000, Summer UROP1000, Summer Compared to male entrepreneurs, female entrepreneurs need to overcome biased evaluation. In this research, we examine if female entrepreneurs frame their entrepreneurial motivation differently than male entrepreneurs, and whether such differences in framing strategy contributes to reducing the bias. We examine our research question in the context of Shark Tank, a popular reality TV show in the United States. Our initial results suggest that female entrepreneurs emphasize their user experience more frequently than male entrepreneurs, even within the same industry. To understand the impact, we plan to examine the implications for fundraising by employing micro-level data and conduct text analysis to see how framing as user-entrepreneur shapes the follow-up questions from investors.
RkJQdWJsaXNoZXIy NDk5Njg=