A deep learning approach to gender equality: Forecasting educational indicators with 1D-CNN aligned with SDG 5

Area of Science:

• Social Sciences
• Education Technology
• Gender Studies

Background:

• Sustainable Development Goal 5 emphasizes gender equality and empowerment.
• Analyzing gender-disaggregated data is crucial for understanding educational disparities.
• Predictive modeling can inform strategies for advancing gender equity in education.

Purpose of the Study:

• To develop and implement a time series prediction model for gender-related educational outcomes.
• To analyze temporal patterns and discrepancies in educational data across diverse countries.
• To provide actionable insights for stakeholders promoting gender equity.

Main Methods:

• Utilized a 1D Convolutional Neural Network (1D-CNN) deep learning model.
• Analyzed gender-disaggregated demographic, socioeconomic, and educational data.
• Trained the model on verified historical data for realistic trajectory predictions.

Main Results:

• The 1D-CNN model successfully predicted gender-related educational results.
• Identified temporal patterns and discrepancies in educational progress.
• Generated country-specific progress trajectories for gender equity.

Conclusions:

• The model offers valuable predictions for gender-focused educational measures.
• Findings support evidence-based planning and targeted interventions for gender equity.
• The study contributes to advancing gender equality in education and beyond.