Uma abordagem de ciência de dados em uma análise socioeconômica de preços para viagens de transporte por aplicativo Uber

Abstract

Studies that use data from the transport company Uber showed that there are factors that contribute to the increase in prices of its travel services. In this context, this research aims to analyze travel routes for low-income users and contribute to reducing these prices. For this, we sought to answer: If a financial center were closer to economically poorer neighborhoods, would there be a change in the average prices of these trips? Could this change financially improve the lives of low-income people? The purpose of our research to answer these questions was to investigate this factor of financial concentration in territorial regions through a Data Science process, analyzing prices and socioeconomic data in the South American city of Fortaleza, located in the country Brazil and from the North American city of Boston, located in the United States of America. Thus, it would be possible to show whether Uber users who live in financially poorer neighborhoods and use this travel service end up paying more than users in richer neighborhoods, when the destination is the financial center. The analyzes and results obtained for Boston served as a validation by analogy for the results obtained for Fortaleza. The analyzed database for Boston refers to a real dataset, available in the Kaggle online community. The database analyzed for Fortaleza was built during our work and is also available on the Kaggle online community, which can serve as a tool for future analysis in other research. To build this base, information from Fortaleza about traffic, peak times, days of the week, number of trips and the Uber price simulator were used. To achieve the objective of the research, the methodology used consisted of the steps of Obtaining and Construction of prices, Obtaining Socioeconomic Data, Exploratory Data Analysis, Cleaning and Processing of Data, Construction of Machine Learning Models and Analysis between the Socioeconomic and travel prices to the cities under study. As results obtained, it was observed that, in a more decentralized scenario of a financial center, low-income users of Uber in Fortaleza could have their trip prices reduced by about 43.07%. This reduction would represent a monthly savings of around 18.82% of their Average Personal Income. For users living in wealthy (high-income) neighborhoods, this decentralization would increase travel costs to just over 100%. However, this increase would represent 6.71% of their Average Personal Income. Future research can expand the results obtained here, optimizing the created database and modifying the Data Science process used.