Case Studies

Harnessing Machine learning and AI for Students’ Academic Success at One of the Top 10 Worldwide Business Schools

4 min read

Published on November 4, 2024

Solutions: Data Strategy & Analytics
Harnessing Machine learning and AI for Students’ Academic Success at One of the Top 10 Worldwide Business Schools
One of the top worldwide business schools recently worked with JAKALA on a machine learning and AI project to improve its students’ long-term success. Using the university’s accumulated data, we developed a machine learning model that uncovered insights into the critical factors influencing student career success and fulfillment post-graduation. Generative AI was then employed to parse student documents, certifications, and curricula, enriching and improving the data available for the model. This highly accurate Graduate Fulfillment Model predicts student fulfillment after graduation and identifies actions to enhance it. With this information, the university can better support its students from their first day of school through to their post-graduation careers, maximizing their chances of long-term success. Generative AI automates document parsing, vastly reducing the time and costs associated with manual data collection by internal teams.

At a glance

53

hours saved (per 2,000 certifications)

330

hours saved (per 4,000 curriculum vitae)

110+

variables analyzed 

Context & Challenges

With a wealth of accumulated data underutilized, the leading university sought to develop predictive models using machine learning to benefit both the university and its students. After reviewing several options, the university selected a model that measures the variables affecting students' ability to secure jobs post-graduation and their levels of career fulfillment. 
 
Student documentation, certifications, and curricula presented a significant opportunity for additional data collection. By using generative AI to parse these documents, the process became more efficient and cost-effective compared to manual data entry. 

Our approach and solution

A Predictive Model to Help Students Excel After Graduation 
The prestigious business school aimed to develop predictive models leveraging years of accrued data and remained open to a wide range of possibilities. Having previously collaborated with the JAKALA team on technology, data management, and business intelligence solutions, the university entrusted us to explore a variety of ideas. 
Ultimately, the Graduate Fulfillment Model was chosen, which evaluates both the likelihood of graduates securing a job and their fulfillment with their careers. This university prioritizes student success and career satisfaction, making this model essential to the school’s mission. 
The Graduate Fulfillment Model aims to: 
  • Identify the key variables in students' educational journeys, and also external contextual variables, that impact their likelihood of career fulfillment.  
This model allows the university to predict future student satisfaction and focus on improving it throughout the two-year period. With insights from the model, the university can enhance its data assets and analytic capabilities to further support career development and student satisfaction. JAKALA also developed a dashboard that gives stakeholders easy access to student fulfillment forecasts and recommended actions to improve them. Additionally, integrating new data into the model enables continued improvement in student outcomes over the two-year period. 
Other potential models JAKALA presented: 
  • Improving student retention 
  • Improvement of student performance 
  • Optimization of course planning 
  • Identifications of behavioral patterns 
  • Improving the effectiveness of teaching 
  • Optimization of admission processes 
  • Personalization of student experiences 
  • Forecasting course demand 
  • Identification of funding opportunities 
  • Optimization of university operations 
  • Identification of skills required by the labor market 
  • Improving the teacher selection process 
  • Identification of training needs of academic staff 
  • Forecasting recruitment costs and optimizing marketing activities 
  • Predicting the academic performance of international students 
 
More Efficient Data Parsing with Generative AI 
Generative AI enables efficient parsing of documents such as resumes and certifications in various formats, extracting specific information for streamlined analysis. In the next phase of our project with the university, we applied generative AI to parse student documentation, including certifications and curricula. Using generative AI did not just allow the extraction of simple information already contained in the curriculum vitae (CVs), but also enabled the reprocessing of data to generate new insights and new types of aggregated information from the CVs. 
We created an AI-driven process that automatically analyzes and collects data from student resumes and certifications, which integrates seamlessly with the university’s existing data lake. This enriched dataset enhances the model’s accuracy, providing deeper insights into the variables that impact students' post-graduation success and fulfillment. 
Primary Goals: 
  • Expand the university’s knowledge base by incorporating new, structured, and organized data from alumni. 
  • Streamline processes by using AI to analyze alumni resumes and certifications. 
  • Maximize employability outcomes through the predictive analysis model enhanced by AI-generated data. 
 
Impact on Marketing: Enhanced Data and Reduced Costs 
By applying AI to document parsing, this leading university significantly improves its data volume and quality, enhancing accuracy and performance. These insights create new marketing opportunities and streamline internal operations. Automation reduces the costs associated with manual data entry, making the process more efficient overall. 
Time and cost savings resulting from using AI are already apparent and impressive. For parsing certifications, it takes about 2 minutes of a person's time to interpret and catalog a certification. We analyzed about 2,000 certifications in the first round, saving approximately 53 hours (which is 7 working days). For CVs, it took around 5 minutes, and by analyzing about 4,000 CVs, they saved about 40 working days (approximately 330 hours). 

Technologies

Microsoft Azure 

Results

  • 01

    Actionable Recommendations for Stakeholders & Marketing

    The model generates specific, actionable insights for university administrators, enabling them to enhance student career fulfillment at every stage of their academic journey. 

  • 02

    Increased Data Accuracy and Insights

    Generative AI enhanced the quality, quantity, and reliability of the data, resulting in more precise predictions and deeper insights into student success. 

  • 03

    Cost and Time Efficiency Gains

    Automating document parsing will significantly reduce the time and costs associated with manual data collection by internal teams, freeing resources for higher-value activities. Results already show savings of roughly 53 hours per 2,000 certifications and 330 hours of savings for CVs. 

TECHNORETAIL_HERO_INSIGHT_2200x1222_OWNED-copy

Discover more about JAKALA's unique offering

Solution

  • Activations

Industries

  • DXP - Digital Experience Platforms

Insights

JAKALA and OMNI.PRO: A Strategic Alliance to Strengthen Leadership in the Adobe Experience Cloud Ecosystem Across the Americas and Europe
Article

JAKALA and OMNI.PRO: A Strategic Alliance to Strengthen Leadership in the Adobe Experience Cloud Ecosystem Across the Americas and Europe

3 min read
JAKALA celebrates GIS Day with technology, innovation, and AI!
Article

JAKALA celebrates GIS Day with technology, innovation, and AI!

3 min read
Innovation and personalization: the future of Customer Experience in Pharma Retail
Article

Innovation and personalization: the future of Customer Experience in Pharma Retail

2 min read
JAKALA inaugurates new offices in the 22@ District of Barcelona!
Article

JAKALA inaugurates new offices in the 22@ District of Barcelona!

2 min read