Drexel LeBow’s business analytics programs provide a curriculum that covers the entire life cycle of data analysis. Drexel’s national leadership in experiential learning shapes the curriculum with a focus on the program’s three pillars: statistics, data management and business modeling.
LeBow is uniquely positioned to address descriptive, diagnostic, predictive, prescriptive and preemptive questions across the business analytics life cycle, from the corporate generation of data through the application and impact on managerial and leadership decision-making and innovation.
What Is Business Analytics?
Identifying the business question through:
- Hypothesis testing
Developing a solution with modeling techniques from:
- Decision sciences
- Finance and economics
- Behavioral sciences
Using various types of data such as:
- Structured (numerical, text)
- Unstructured (visual, audio, social)
Analyzing data with:
- Quantitative techniques (statistical)
- Qualitative techniques (ethnographic)
Deriving value in terms of:
View a full list of degree programs in business analytics offered by the LeBow College of Business:
- Information Systems Strategy
The strategic decisions around the design and management of information systems have an enormous impact on an organization’s capabilities to deploy analytics tools and gather business insights and intelligence. Research at LeBow focuses on key issues such as design of systems, outsourcing and technology adoption. Application areas include health care systems, global supply chain management and social media strategies.
- Data Mining
Data mining is a process for exploring large data sets for patterns and relationships, and it plays a crucial role in predictive analytics for big data. Research at LeBow focuses on mining structured and unstructured data, including data capture/collection, storage and management, statistical analysis for structured data, and text mining. Application areas include health care management, cyber-crime and cybersecurity, operations management, and marketing.
- Applied Econometrics and Forecasting
Applied econometrics is the field of developing empirical quantitative models of the economic and business environment in order to develop sound forecasts. Research at LeBow focuses on building and using complex time series models, estimation techniques and Bayesian statistics, as well as the performance and reliability of econometric software. Application areas include financial modeling and forecasting, educational assessment, antitrust and regulation, and operations management.
Insights and intelligence gained from data analysis can be used to improve business decisions. Optimization is a powerful technique for decision-making and falls into the categories of prescriptive and preemptive analytics. Research at LeBow focuses on the how to formulate and solve complex and large-scale optimization models, building customized software packages and decision support systems to do so, and incorporating risk management concerns, dynamic environments and competition into the decision framework. Application areas include portfolio optimization, operations and supply chain management, and decision-making in the public sector.
Recent Selected Publications
Murugan Anandarajan, PhD, professor of management information systems, published the chapter, IoPTS and the Future Workplace: A Global Perspective, in the book “The Internet of People, Things and Services,” which he also co-edited. The chapter introduces an IoPTS adaption score to classify national progress in adopting and using IoPTS. It also explains the importance of understanding a country’s IoPTS readiness, which is vital for the effective implementation of the future global workplace.
Elea Feit, PhD, assistant professor of marketing, published a paper in Transportation Research Part B that focuses on methods for predicting what type of vehicle a customer will choose. The types of models she focuses on are used by policymakers and manufacturers to understand how consumers will react to the introduction of more alternative fuel vehicles.
Feit has begun a new project that focuses on designing A/B tests for websites and emails. Her approach focuses on the profit to be gained by the test, which is different from experimental design methods used in medicine and science.
Matthew Schneider, PhD, assistant professor of decision sciences and MIS, published a paper in Marketing Science developing a flexible methodology to protect marketing data. A key feature of the method is the trade-off between meeting the needs of the data users and reducing the risk of disclosure to data intruders. Schneider and co-authors demonstrate that their methodology performed well relative to other data protection methods.
Chaojiang Wu, PhD, assistant professor of decision sciences and MIS, in collaboration with two additional faculty members, developed a decision model for managing risk and measurable uncertainty. The work is published on IISE Transactions, the flagship journal of the Institute of Industrial and Systems Engineers. The innovative model allows decision makers to optimally choose decision alternatives to manage risk.
Wu, in collaboration with Chelsey Hill, PhD, assistant professor of information and business analytics at Montclair State University; and Erjia Yan, PhD, assistant professor of information science in Drexel’s College of Computing & Informatics, analyzed knowledge flow among six business disciplines using citation data from more than 200 business journals. Their research is published in the Journal of Informetrics. The paper identifies increasing diversity of knowledge sources, or knowledge diffusion, in most business disciplines. The paper also quantifies a “badge effect” for top-tier designated journals, suggesting that inclusion in a top-tier journal signals journal quality, which is already known within-discipline, to the greater business research community.
Wu also published a study on the cross-disciplinary examination of whether funded research leads to greater impact in journal citations. The study finds that, while there is an overall positive effect, the effect is magnified by factors of multiple authorships and multiple institutions for STEM disciplines. The study has been accepted for publication in Scientometrics.