Phase 2 Linking Soft Skills and Labor Market Outcomes

Overview

In certain developing countries, young people are often disadvantaged when entering the job market due to a lack of access to education. The World Bank is seeking to encourage the development of soft skills in countries where educational access is more limited, as to emphasize the importance and value of soft skills across various industries. Through this process, it is hoped that unemployed youth in these regions have better opportunities to enter the job market by signaling their interpersonal skills. The Cal Poly Digital Transformation Hub (DxHub) powered by Amazon Web Services (AWS) collaborated with Cal Poly faculty and students and the World Bank’s Poverty and Equity Global Practice to continue research in understanding how one can predict an individual’s fit in a specific job or industry based on the soft skills they possess. Instead of a data-agnostic approach that was utilized by the first group of students who led this challenge, students from the MSQE program at Cal Poly implemented machine learning and an econometric approach to understand the issue.

Innovation in Action

This challenge first began in 2021, Samantha de Martino, an economist with the World Bank’s Poverty and Equity Global Practice Group, collaborated with a group of Cal Poly students from the Data Science Capstone class under Dr. Dennis Sun and Dr. Jonathan Ventura. This collaboration took the first steps by using a data-agnostic approach in order to extract and measure specific soft skills, specifically with US datasets. The goal was then to create a predictive market success model by using measurable soft skills with demographic variables as predictors, which then allowed them to subset data by specific industries. Through developing a generalizable model, it was then intended that it can be used across different countries in determining the soft skills preferred across different countries and industries.

This challenge was later continued by a group of Cal Poly MS Quantitative Economics students under the supervision of Dr. Carlos Flores during Spring & Winter 2022. Here, the students implemented a different technique, instead opting to use machine learning and an econometric approach to predict how well an individual can fit into certain industries depending on their soft skills. Utilizing data from the National Longitudinal Survey of Youth 1997 (NLSY97) as their main dataset, they created parameters for five soft skill categories based on the work done by the previous student group. They ended up utilizing both disaggregated and aggregated data, with disaggregated data providing better accuracy and aggregated data providing more interpretability. Along with the machine learning and econometric approach, students also used factor analysis to provide a sort of internal consistency check as a comparison. Their findings were then visualized in various ways, including response models, a confusion matrix for top industries, and neural net representations. Students utilized AWS resources specifically to test their models and house all datasets that were utilized in this challenge.

 

Conclusion

While prediction accuracy was relatively low due to the limitations within the data, the student’s exploration and findings through their machine learning and econometrics methods provide a very promising foundation for future research. Students were able to effectively categorize and measure soft skills based on the NLSY97 data, which means that the models can continue to be tested based on their method. By implementing more complex machine learning models and even exploring their technique with other datasets, especially with datasets that apply to the target population, their work can be expanded upon to find more accurate ways to link soft skills and labor market outcomes.

Supporting Documents

Student Paper

Authors: Matt Gevercer, Zoe Krieger, Diego Saavedra, Benjamin Schneider, Benjamin Zwarg

About the DxHub

The Cal Poly Digital Transformation Hub (DxHub) is a strategic relationship with Amazon Web Services (AWS) and is the world’s first cloud innovation center supported by AWS on a University campus. The primary goal of the DxHub is to provide real-world problem-solving experiences to students by immersing them in the application of proven innovation methods in combination with the latest technologies to solve important challenges in the public sector. The challenges being addressed cover a wide variety of topics including homelessness, evidence-based policing, digital literacy, virtual cybersecurity laboratories and many others. The DxHub leverages the deep subject matter expertise of government, education and non-profit organizations to clearly understand the customers affected by public sector challenges and develops solutions that meet the customer needs.