Paper Title
Trade Flow Estimation Between Global Economies Using Machine Learning Techniques

Abstract
Bilateral trade flow between global economies has been a critical economic indicator for economists and policymakers owing to its potential to significantly influence international trade sanctions and policies, which profoundly impact international relations.This deep-rooted global interdependence has been historically simulated by the international economy, which engenders substantial mutual benefits for participating companies. The analysis of various economic trends and the generation of accurate future predictions have become indispensable pursuits since the inception of predictive machine learning models. By meticulously examining historical economic data and constructing relevant fine-tuned machine learning models, it is possible to attempt to predict future events and capital flow between countries. The reliable estimation of bilateral flow is of paramount importance, and the use of machine learning techniques for economic forecasting, leveraging the unreasonable effectiveness of data, in lieu of traditional statistical methods, can help in achieving exceptional predictions. In this study, we endeavor to enhance traditional statistical methods by experimenting with several time-agnostic machine learning models. Keywords - Artificial Intelligence, Data Mining, Business Analytics, Neural Networks, Gradient Boosting, Bilateral Trade Flow