We offer on-campus engagement tools for companies of all sizes across industries to raise brand awareness and recruit students.

Industry Partners
Past Project Highlights

Demand Based Pricing

Sponsor: Chicago Park District, Fall 2018

The Chicago Park District (CPD) has numerous unique indoor and outdoor facilities made available for people to come together for various occasions, including special events such as: weddings, athletics, corporate gatherings, music festivals, and picnics. CPD’s Department of Revenue provides thousands of permits for these special events.

The goal of this project was to gain insight on CPD’s customer segmentation around price elasticity and price sensitivity, and to find a solution for implementing strategic pricing decisions.  The MLDS team developed a time series forecasting model to account for the trend, seasonal and cyclical demands for the events. This solution offers a good measure to base price markups or markdowns within each seasonal cluster.

Predicting Hotel Demand

Sponsor: Sabre, Fall 2021

Sabre is a software and technology company that powers the global travel industry. With decades of revolutionary firsts, the company drives innovation across the travel ecosystem partnering with airlines, hoteliers, agencies and other travel partners to retail, distribute and fulfill travel.

For the last several years Sabre has been supporting the Master of Science in Machine Learning and Data Science program at Northwestern University by providing a business problem to a group of students taking an ML course and then guiding them in solving it.

In 2022 we collaborated on a project that aimed to predict weekly total room-nights for hotel bookings up to four weeks into the future, using previous hotel bookings, air passenger traffic volume, air shopping data, holidays, and seasonality. Three different model types, Prophet, SARIMAX, and Random Forest were used to make these predictions. The team found that the most important predictors vary for different hotels. Therefore, a stepwise feature selection algorithm was implemented to find the best combination of predictors. The team developed a Python model pipeline that allows a user to select the best model for hotel predictions. This work contributed to a much larger initiative Sabre undertakes to understand the demand for travel and correlations between different components of trips.

Psychometric Models for Workforce Solutions

Sponsor: SurePeople, Fall 2021

SurePeople is a technology innovator specializing in People Science, offering solutions that help organizations tackle workforce challenges with next-generation leadership and team development capabilities.

In this Practicum project, the MLDS team explored the relationship between job family/level and four dimensions of personality from Prism, a psychometric algorithm. The team performed exploratory data analysis with data transformation and applied natural language processing to categorize the job titles into job families and job levels. A predictive model was built using scores across 54 traits and attributes and identified significant (and meaningful) connections across the Prism modules and the personality quadrants. The project team recommended actions to support future work on workforce solutions.

SurePeople Practicum Team members.


"In our experience, the Northwestern MLDS students have consistently brought the intellectual curiosity, technical acumen, business maturity, and collaborative approach necessary to solve relatively challenging problems without a guarantee of success and with a very reasonable level of supervision. Many of them have gone on to take full-time roles as data scientists or analytics consultants on our team, making lasting contributions to our machine learning stack, client relationships, and in many other areas. Any institution looking to explore innovative data science solutions should consider sponsoring a Northwestern MS in Machine Learning and Data Science Practicum project team."
- Michael Umlauf, Senior VP, Global Data Science and Analytics, TransUnion

  • "The students impressed our team with the work they put together. We are excited to continue working on the project and feel that we have a strong foundation thanks to the  MSiA [renamed MS in Machine Learning and Data Science] team."​
  • "I had an amazing experience working with Northwestern team. It was not an easy problem to solve and the team put in a lot of hard work and effort to develop a compelling business solution for [our company]."​
  • "The students had an obvious strong skill set and had the willingness to work diligently on a difficult problem." ​​
  • “The students did a phenomenal job! Beyond my expectations. They are equipped for great things. They understand the problem and applied smart solutions.”​
  • “We let the team decide their own roles, cadence, and style of working together. We kept tabs on how well they were collaborating with each other and were happy to see positive marks on this.”​
  • “The students worked well as a team and each student took the lead on a separate task. We held weekly meetings where the students showed their progress and received feedback from the sponsor. It was also nice to see that the students tried some paths that didn't work as well as the final solution.”​
  • “They did really a good job. They were communicating with each other and also having weekly meetings with us. They were also asking the right questions and getting information from us. Individual team members had their own responsibilities and delivered them.”​