Riipen
Log in Sign up

Masters' Big Data Analysis w/ Machine Learning

INSY 5376
Closed
University of Texas at Arlington
University of Texas at Arlington
Arlington, Texas, United States
Sridhar Nerur
Professor
2
Timeline
  • September 30, 2017
    Experience start
  • October 16, 2017
    Project Scope Meeting
  • December 1, 2017
    Experience end
Experience
6 projects wanted
Dates set by experience
Preferred companies
Anywhere
Any organization
Any industry
Categories
Skills
data analysis information systems storytelling analytics
Learner goals and capabilities

Master's-level student-consultants will develop a tailored strategy for your organization using data analytics and machine learning algorithms, designed to address a challenge or opportunity specific to your needs.

Learners
Any level
72 learners
Project
25 hours per learner
Learners self-assign
Teams of 4
Expected outcomes and deliverables

The project deliverables are:

  • A 10 to 15 page project report that gives a clear idea of the problem, the steps taken to prepare the data, the predictive models that were evaluated, and the rationale for the recommended model.
  • A 20 minute presentation in class.
  • The slides that were used in the presentation.
Project timeline
  • September 30, 2017
    Experience start
  • October 16, 2017
    Project Scope Meeting
  • December 1, 2017
    Experience end
Project Examples

By applying data management and machine learning concepts, students will draw actionable business insights from a large dataset and solve a major challenge for your business.

A group of four Master's-level students will work on a challenging Big Data-related business challenge.

Examples of previous projects include the following:

  • Using Zillow and county data to predict the housing prices
  • Examining companies’ annual reports/10-K filings to cluster companies with a view to understanding how and why they are similar/dissimilar
  • Using Yelp data to understand the factors of customer ratings and how they impact performance
  • Analyzing tweets to predict the winners at the Oscars

In addition, the students typically look at publicly available datasets related to a variety of problems, including fraud detection, predicting the quality of wine, predicting whether or not someone has cancer based on various criteria, predicting customer churn, understanding customer behavior from an analysis of clickstream data, and so on.

Project examples include, but are not limited to:

  • Predictive analytics in ecommerce & retail: Which products/categories to market to a customer, given the customer profile?
  • Predictive analytics in investments & trading: Which stocks or securities to purchase following a sequence of events?
  • Pricing for new technology products & services: How to price a new tech product, based on competitive, customer, and transactional data?
  • Credit scores & ratings: How to assess the credit risk of a borrower, based on the borrower profile and meta data?
  • Financial fraud likelihood: What is the likelihood of fraud for a user attempting to access your personal finance solution?
  • Customer segmentation & targeting: What value to assign to a customer based on the past purchase and/or transactional data and customer profile?
Companies must answer the following questions to submit a match request to this experience:

Provide any necessary data (NDAs can be signed).

Upon completion of the project, your organization should provide feedback on the students’/group’s performance.

Be available for questions from students.

The educator will be available to answer any questions that you or the students may have.