Data science for business decisions is about leveraging data and data analytic methods to better achieve business objectives. Successful business analysts, managers, and executives are increasingly required to leverage newly available data sources – voluminous and varied – to inform their decisions about how to best run their businesses. This book presents a practical data-to-decision methodology, a rigorous study of data analytic methods, case studies, and a practicum on implementation skills. It introduces and delves into exploratory data analysis based on statistics and data visualization, descriptive and predictive modeling based on machine learning, and data-driven decision making based on model evaluation. Discussions and examples guide students through how these methods work, expose their individual strengths and weaknesses, and show how to apply them for better business results. The case studies, based on real industry data, elaborate on their usefulness.
This book is intended for undergraduate and graduate business students with special interest in data science, data science students with special interest in business, and other students with interest in both. It sits at the sweet spot in between a cursory survey of business-oriented data science concepts and an in-depth study of statistical learning theory. Data analytic methods are presented here by appealing to intuition, backed up by an appropriate level of mathematical rigor, but retaining focus on their business applications. The balance makes the material accessible to students with a broad range of backgrounds - those looking for “So that’s how it works!” and those looking for “So that’s what it’s for!” Students will come away well-positioned and well-differentiated for their future industry, consulting, and government roles as data-savvy business practitioners.