EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
1598. Breaking Barriers: Unveiling Gender Disparities in Corporate Career Paths Using Deep Learning
Invited abstract in session MD-31: Network Analytics, stream Analytics.
Monday, 14:30-16:00Room: 046 (building: 208)
Authors (first author is the speaker)
| 1. | Cristian Bravo
|
| Department of Statistical and Actuarial Sciences, Western University | |
| 2. | Yuhao Zhou
|
| Department of Statistical and Actuarial Sciences, Western University | |
| 3. | Wenhao Chen
|
| Department of Statistical and Actuarial Science, Western University | |
| 4. | María Óskarsdóttir
|
| Department of Computer Science, Reykjavik University | |
| 5. | Collins Ntim
|
| Southampton Business School, University of Southampton | |
| 6. | Matt Davison
|
| Applied Math and Statistical & Actuarial Sciences, University of Western Ontairo |
Abstract
This study delves into the interplay between gender, professional networking, career-path trajectory, and board director appointments in Canadian publicly traded companies. To obtain our results, we combine multiple publicly available sources into a unique dataset. This dataset (consisting of over 700 Canadian firms covering more than 19,000 senior managers and board members in the 2000-2022 period), charts detailed network information of both senior managers and board members across five key dimensions: education, current and prior employment, and current and prior social engagement. By matching senior managers of both genders based on their career trajectories and backgrounds, and applying Long Short-Term Memory (LSTM) deep learning alongside network analysis, our research uncovers the distinct network influences impacting the board appointment prospects of women versus men. The findings causally demonstrate a “glass ceiling”, suggesting that women necessitate more substantial networking credentials than men to secure equivalent corporate board positions, when controlled for career paths and backgrounds. This paper outlines our data compilation process, matching and analytical methodology, presents our empirical results and insights, and the broader implications these hold for policies aimed at encouraging both good corporate governance and gender equality at senior level.
Keywords
- Analytics and Data Science
- Complex Societal Problems
- Social Networks
Status: accepted
Back to the list of papers