Análisis de datos y desarrollo de un sistema de inteligencia artificial para la detección de la tasa de aprobación de visas a estados unidos

Abstract

This article presents an analysis of the profiles of individuals who are approved or denied tourist visas in Colombia using data mining through the CRISP-DM methodology and computational intelligence, taking into account 2 crucial factors. 1. The denial rate is approximately 46%, which means that Colombians spend nearly two million dollars on rejected visas. 2. Visa interview appointments are delayed by two years after the emergence of COVID-19. supported too by other investigations like Prateek and Karun who used classification algorithms to detect profiles and predict results of study visas , our analysis obtains information about the patterns and common characteristics among applicants who have obtained approval for their tourist visa, such as their age, gender, nationality, marital status, profession, among other aspects related in the application forms (DS-160). The analysis concludes with the development of an AI calculator capable of predicting the approval probability with an effectiveness of over 85%. Ideal for applicants who could see which points are relevant to improve or simply not show up and wait for the right moment.