Description: Data is big everywhere. This class provides the fundamental skills of the 21^st century - understanding data, extracting knowledge, generating predictions and visualizing the results.

Instructor: Sriraam Natarajan, Informatics East, 257. natarasr@indiana.edu

Class Timings: Mondays and Wednesdays 5:45 PM - 7:00 PM Ballantine Hall (BH) Room 215

Office Hours: Mondays and Wednesdays 3:00 PM - 4:00 PM Informatics East, 257

AI: Mayukh Das, maydas@indiana.edu. Office hours: Tuesdays and Thursday 4:00 - 5:30 PM. Informatics Connector 2nd Floor.

Information: There is no doubt that we operate in a world of data. We, ourselves are not responsible for only creating the data, but also securing, managing, and deriving actionable intelligence from data. This course will provide the necessary tools to access, create, manipulate, analyze and visualize the data. The intent of the course is to use real data sets from a wide variety of disciplines including health care, business, humanities, demographics etc. to make the learning of data fluency contextual for the student. Throughout the course, a variety of computational tools will be used by the students to discover patterns and solve problems. Students will be informed of the underlying theories behind the techniques to better understand the tools and be equipped for future problem solving based on extensions of the key learning outcomes of the course.

Textbook: Class slides will be posted. I highly recommend the book - Doing Data Science (Rachel Schutt & Cathy O'Neil) O'Reilly 2013.

Learning Outcomes: At the end of the class, students will have satisfactorily demonstrated that they can:

1. Describe the nature of the data, how it is structured, stored and accessed – relational models and tables
2. Derive information from data and support conclusions or recommendations based on evidence existing in the data – data mining and predictive modeling.
3. Analyze and present the data - visualization

Assessment: Exams (40%), Final Exam (20%), quizzes (5%), mini-project (10%) and Data analysis homeworks (25%)

Topics Covered

1. What is Data Science?
   • Big Data and Data Science Hype
   • What can data analysis discover - A case study with Adverse Drug Events
   • The current Landscape
   • Skills of data scientists - learning application domain, communicating with uses, seeing the picture of a complex system, know how data can be represented, transformation, visualization, analysis and ethical reasoning.
2. What is Data?
   • Data definition - bits to bytes to larger structures
   • Data collection
   • Data storage - Text to rows and columns to Excel sheets to relational data bases
   • Accessing and using data - A project with Excel (Case Study and Homework) and a project with rows and columns in a single table
   • Data Visualization
3. Exploratory Data Analysis
   • Statistical Inference
   • Populations and Samples
   • Analysis of Histograms
   • Introduction to Probability as fractional counts
   • Exploratory Data Analysis
   • Case Study: RealDirect - How do they make money?
4. Mining the Data
   • Case study and application - Spam Filter
   • Introduction to learning - What can be learned
   • Algorithm - Linear Regression
   • Algorithm - Decision Tree
   • Algorithm - k-nearest neighbor
5. Big data
   • What is the hype? What is big data?
   • Populations and samples of Big data
   • Big data = big assumptions?
   • what are the technologies? Parallel computations - An example.
   • Case study - Watson project
6. Successful Applications
   • Financial Modeling
   • Recommendation Engines
   • Fraud Detection
   • Social Networks
   • Medical Applications
7. Into the future
   • Crowdsourcing
   • What are next generation data scientists - Problem solvers, soft skills, asking the right questions
   • Being the ethical data scientist

Tentative Schedule