World Data of Gender Inequality Prediction

Keywords: World, Data

Background

This study utilizes artificial neural networks (ANN) to predict gender inequality levels based on world data. By analyzing social - economic factors, education levels, and workforce participation rates, a predictive model is developed and trained using preprocessed data. The model shows promising accuracy in predicting gender inequality levels across countries, offering valuable insights for policymakers and organizations to address and mitigate gender disparities globally. Obtaining reliable and comprehensive world data on gender inequality can be challenging. Ensuring the data is accurate, up-to-date, and covers a wide range of countries poses a significant challenge. The model needs to be able to generalize well to diverse regions and countries with varying socio-economic and cultural contexts. To provide valuable insights to policymakers and organizations in addressing and mitigating gender disparities on a global scale. As it was a regression problem statement to predict the GII values, means the square error is used as a loss. The linear activation function is used in hidden layers, after running 50 epochs with batch size 32, the loss is 0.20137, whereas the mean squared error is 0.1767. R-square score is -2.7673.

Aim & Objectives

Aim
To predict the Gender Inequality of World Data using DL techniques
Objective

Utilize an ANN model to predict global gender inequality trends, providing insights into socio-economic disparities.
Develop an ANN system that analyzes diverse data sets to forecast gender inequality variations across regions.
Evaluate the ANN's prediction accuracy in capturing gender inequality dynamics, contributing to awareness and policy discussions.

Research Methodology

ANN Technique used

Software & Tools

Jupyter, Google Collab

— Preview truncated. The complete document (full chapters, references, diagrams, and appendices) is shared with clients as part of project delivery. —