Back To Projects
Improving User Retention in Video Game Industry
Ethan V.

This research paper delves into the intersection of player data analytics and affective computing to predict and adapt game difficulty levels for the purpose of enhancing player retention in the gaming industry.


This research paper delves into the intersection of player data analytics and affective computing to predict and adapt game difficulty levels for the purpose of enhancing player retention in the gaming industry. The study used two Kaggle datasets which include a facial emotion dataset and real-time call of duty player data. A novel emotion detection model, leveraging transfer learning, is constructed to discern a spectrum of emotions from player facial expressions. The emotional context extracted from this model is seamlessly integrated with player data, facilitating a supervised learning task centered on predicting changes in game difficulty levels—a pivotal factor in player engagement. Several machine learning models including K-Nearest Neighbors, Decision Trees, Random Forests, MLP Classifiers, AdaBoost, and Gaussian Naive Bayes were employed to use emotion and player data to predict difficulty changes that will raise player retention.

Explore More!

Ethan V.
Anjali Singh

Related Projects

Using Machine Learning Models to Determine Medical Features Most Indicative of Gestational Diabetes

With the recent overruling of Roe v. Wade, pregnancies have become especially dangerous since many females who previously abort fetuses no longer can. By doing this research project, I can help figure out what medical factors may lead to gestational diabetes, and hopefully from there, the results can be used to counteract those features.
Fiona B.
Mentored by
Structure-Based Analysis of Parkinson’s Disease Protein Mutations: Comparative Analysis of Computational and Experimental SNCA Structures

This study uses AI-based protein modeling tools such as AlphaFold and ColabFold to compare wild-type and mutant α-synuclein structures in Parkinson’s disease, evaluating their interactions with pharmacologically relevant ligands. By integrating structure prediction with molecular docking, the research highlights both the potential and limitations of computational methods for understanding mutation-specific effects and guiding drug discovery efforts.
Arya S.
Mentored by Khanh Nguyen
The Impacts of Child-Mentor Relationships on Child Mental Health

In this paper, we use a dataset from the Substance Abuse and Mental Health Data Archive to analyze the impacts of child-mentor relationships on child mental health. Previous studies have come to similar conclusions: positive parent-student and teacher-student relationships often lead to signs of positive mental health in children. To expand upon these past findings, we used different measures of mental health and relationship qualities to create a predictive model. We conducted classification and coefficient weight analyses to see how strong of an impact different variables representing indicators of healthy relationships had on different aspects of child mental health. This information was used to create predictions of future cases. Like previous studies, we found that there was a general pattern that showed that good child-mentor relationships, defined specifically by the frequency of praise and fights, had an overall positive impact on child mental health, specifically when it came to symptoms of depression. Furthermore, parents seemed to have stronger impacts on child mental health than teachers did. Limitations include possibly biased respondents who may not be representative of the greater population, as well as the specificity of the variables that were chosen. Going forward, further steps to analyze different datasets and deepen the scope of the research will be helpful in finding patterns and developing more detailed conclusions.
Samantha K.
Mentored by Akshay Jagadeesh