Prediction of Peruvian Companies' Stock Prices Using Machine Learning

• Autores: Espiritu Pera, Jose Antonio, Ibañez Diaz, Alexis Oneil
• Formato: tesis de grado
• Fecha de Publicación: 2024
• Institución: Universidad de Lima
• Repositorio: ULIMA-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.ulima.edu.pe:20.500.12724/21096
• Enlace del recurso: https://hdl.handle.net/20.500.12724/21096
• Nivel de acceso: acceso abierto
• Materia: Acciones (Valores); Empresas; Algoritmos; Aprendizaje automático; https://purl.org/pe-repo/ocde/ford#2.11.04

Nowadays, the challenges that covid-19 has generated to the financial community that operates within the stock market has generated a greater uncertainty in the profitability and consequently has made this practice more difficult. To overcome that problem the present study aims to develop a model that facilitates this work; this model uses the SVR regression algorithm and through technical indicators provide us with the possible trend that the stock may take in the future and thus suggest that the investor in question buys, sells or holds the stock in view of that result. As a result of the project, it was proposed to use 7 technical indicators RSI, MACD, ROC, WMA, OBV, the Williams indicator and the stochastic oscillator that determine the current market condition. After validating the model, it was concluded that there are different Peruvian companies that have been able to overcome the difficulties of the pandemic with enough growth potential during this post-covid period. Our main research question: Is it feasible to predict stocks in Peruvian companies with growth potential during the Covid-19 pandemic, using the Support Vector Regression (SVR) algorithm as Machine Learning in the Lima Stock Exchange (BVL)?