This project-based course explores and develops applied communication skills needed for analytical professions to make the business case. Students work individually and in teams to develop persuasive messaging to communicate complex technical information and business insights to, and between, technical experts and business decision-makers.

This course focuses on collecting, drawing inference, and making business decisions based on data. It will cover tools — Python, APIs, and NLP — to collect, manipulate, and analyze data from the web and other sources, with the objective of making students data savvy and comfortable with deriving insights from real-world, large datasets. Students will be exposed to the power of clickstream analysis and the possibilities that can be unleashed from industry applications of web data analytics.

Unstructured data such as text, images and video are routinely collected by companies and other organizations. The complex nature and scale of data such as this requires specialized analytics frameworks. In this course we discuss and use tools that empower decision makers to extract actionable

This course focuses on improving the performance of production and service operations, as well as supply chains, through the combination of data and analytical tools including statistics, forecasting, and optimization. Students will learn to employ analytics in capacity and distribution facility planning and contracting; how to determine data collection requirements for dynamic management of inventory levels; and how to improve revenue management under demand learning. Prerequisites: MGTA 451, MGTA 452, MGTA 453, and restricted to master’s of business analytics students or with department and instructor approval.

In this course we will cover the principles of designing and building dashboards and data visualizations. We will leverage Tableau’s library of resources to demonstrate best practices for data visualization and data storytelling.

Students will learn to design and run experiments to guide policy and business decisions. They will learn to distinguish between a correlation and a causal effect and also to critically evaluate causal claims based on nonexperimental data. Prerequisites: MGTA 451, MGTA 452, MGTA 453, and restricted to master’s of business analytics students or with department and instructor approval.

Decision making is difficult with scarce resources, inexact information, and conflicting stakeholder agendas (i.e., most of the time). Students will use advanced behavioral research to gain a competitive advantage, by improving their decisions and their understanding of how others decide. Prerequisites: MGTA 451, MGTA 452, MGTA 453, and restricted to master’s of business analytics students or with department and instructor approval.

Many projects fail to produce valuable results, are over budget, or not finished on time. This course will teach students how to set and manage goals and expectations of the team and of the executive sponsors for business analytics projects. Prerequisites: MGTA 451, MGTA 452, MGTA 453, and restricted to master’s of business analytics students or with department and instructor approval.

This course is devoted to current methods for recommender systems, data mining, and predictive analytics. No previous background in machine learning is required, but all participants should be comfortable with programming (all example code will be in Python), and with basic optimization and linear algebra.

For additional information see: https://cseweb.ucsd.edu/classes/fa19/cse258-a/

Analyzing large-scale and complex data is an integral part of many business applications today. This course is designed to provide students with the skills of handling large volumes of data through database systems. The students will learn fundamental operations like data cleaning and the extract-transform-load (ETL) process that collects data from external sources into a database, advanced levels of SQL to perform complex queries as well as in-database analytics, and principles of data warehouse design for enterprise-level data analytics.

Analyzing large-scale and complex data is an integral part of many business applications today. This course is designed to provide students with skills and knowledge to perform analytics at scale. Students will learn the steps in the analytics process used to gather, prepare, process, and evaluate data. Skills and technologies to perform scalable analytics on big data using distributed computing and cloud-based tools will be the focus of the course. Hands-on experience will be provided with the Spark distributed platform and AWS cloud-based analytics. Through assignments and a project, students will apply the tools and techniques they learn in the course to leverage big data.

In this course you will learn everything you need to know to build statistical/machine learning models to find fraud in data events. We will cover the basics of building fraud models: understanding the problem dynamics, modes of fraud, data analysis and preparation, building expert variables/features, different algorithm choices, and measurements of model goodness. There will be five homework problems and two group projects, with group sizes typically four to six people. We will talk through in detail several examples of fraud problems and solutions, including tax fraud, application identity fraud, healthcare claims fraud, and credit card payment fraud. We will cover the topic of statistical modeling with a drill-down into all steps to building machine learning models. There will be a high-level discussion of a wide variety of statistical modeling methods, including linear/logistic regressions, clustering, neural nets, trees, SVM, random forests, deep learning, boosting and bagging. The overall fraud solution emphasis will be on creating expert variables/features which are the key to building successful fraud algorithms. For each of the two projects the teams will build the fraud algorithms and prepare a presentation and a proper business report, which can then be useful tools for future job interviews. Students are expected to have good backgrounds in math and statistics, and a working ability in any modern programming language that can interact with open source machine learning algorithms, such as R or Python.

This class covers the key drivers for making data-driven pricing decisions. Price setting is one of the most crucial of all tactical marketing decisions. It involves a detailed understanding of both supply-side (e.g. costs) and demand-side factors (e.g., consumer willingness to pay). In this course, we will approach the pricing decision as an intersection of economic, strategic, and behavioral considerations. We will cover the data required and analytical techniques to make optimal pricing decisions. We will cover tools and techniques for primary (e.g., survey) data as well as for secondary data (e.g., POS scanner data). The course will consist of lectures, where we will discuss the theory of pricing, and in-class labs, where we use data to determine the appropriate price to charge. The class will be heavily analytical and a good working knowledge of R, an understanding of regressions, and predictive modeling are required.