|
Data Mining, Analytics, and Information Extraction in Intelligent Business Services: Online Ads, Healthcare, and Service Centers |
|
Collaborative Course Coordinated with UCSC ISM-280I Who should take this course: Graduate students interested in systematically learning analytic data mining, business analytics, statistics, and machine learning techniques, with applications to business management and services (Google, Yahoo, Microsoft, IBM, HP, SAP, Fair Isaacs, Facebook, Cisco and AOL) Engineers and managers who want to Develop a broad and deep understanding of this hot new space including search engines, computational advertising and online marketing, financial and health services, business analytics, business intelligence, and knowledge (performance optimizing) services, including hands-on training (including software) for immediate use at work Transition into this area Brainstorm ideas for a startup (plus some support for entrepreneurial endeavors if requested)
Course Objectives The intent of the course is to focus on several Knowledge Service areas in Business Management, describe the critical challenges and issues, and develop fundamental techniques and methods to solve these problems. Knowledge Services comprises of two aspects or elements: 1. Analysis of data and information to produce knowledge which is provided to the user to assist in understanding, knowledge discovery, and alerts for decision making purposes, such as a potential failure of an electronic system, or an ad opportunity alert, and 2. Decision making to deliver actual physical or other services, such as in a call or service center. Our focus in this course will be on the former aspects of knowledge computation and alert; the decision making for achieving service delivery will be consider in subsequent courses. We will specifically consider: Application areas: Online marketing and computational advertising, support services for operations and innovation, financial services, entertainment, and healthcare Specific topics: Recommenders, fraud detection, anomaly detection, online marketing and purchase probabilities, social networks, support services and centers, healthcare prognostics and diagnostics, financial prediction, text mining, information retrieval, incorporation of human user feedback Techniques: Machine learning, Prediction - Linear Regression, logistic regression, constrained optimization, recommenders, relational learning, time series, classification, text mining and information retrieval We will also cover Information Extraction during the second half of the course. Topics include: - Named Entities Recognition - Relationship Extraction - Sequential Learning - Natural Language Processing - Semantic Role Labeling Software (Data Mining and Statistical) Tools: S and Enterprise Miner (SAS) and or R (Open Source), Matlab, (Plus Weka – open source – for Machine learning, and XLMiner, an Excel add-on for data mining) This course is introductory and will develop the fundamental statistical and machine learning models and techniques for data mining and business analytics progressively, in the context of real world applications and examples. We will develop the techniques systematically and sequentially, but will move back-and-forth the different real world applications and domain areas. Industry speakers and class presentations will provide a broader exposure to topics and leading-edge research and industry practice results. The subsequent courses, such as ISM 250 and 251, will expand on the techniques and domain areas such as web mining, computational advertising and online marketing, social networks and relational learning, reinforcement learning, constrained optimization, and also explore significant projects, including possibly with industry. Prerequisites: Students are expected to be mathematically mature, and to have had prior exposure to undergraduate linear algebra at the level of MATH21 or AMS10 and probability/statistics at the level of AMS 131 or MPE 107. We will provide a refresher in the form of a “boot camp” early in the course, to enable students to relearn basics required for the course.
|
|
Location 254 Sutardja Dai Hall (SDH), CITRIS Building |
|
Time Lecture : Wednesdays 2-4 PM
|
|
ISchool 290 Spring 2011 |
|
Instructors Ram Akella, Ray Larson, Industrial Expert: James Shanahan Email: akella@ischool.berkeley.edu, ray@ischool.berkeley.edu, Telephone: 650-279-3078 (Ram), 510-642-6046 (Ray) Office: 422 Sutardja Dai Hall (SDH), CITRIS Building Office Hours: 4-5 PM, Wednesday, by appointment |
|
Home (Course Video Playlist) |
