• Home
  • Kleyton da Costa
Kleyton da Costa

Kleyton da Costa
Holistic AI

BSc in Economics

About

7
Publications
940
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1
Citation
Introduction
My research interests include time series forecasting, macroeconometrics, artificial neural networks, and explainable AI.
Education
March 2017 - July 2021

Publications

Publications (7)
Preprint
Full-text available
Gross domestic product (GDP) is an important economic indicator that aggregates useful information to assist economic agents and policymakers in their decision-making process. In this context, GDP forecasting becomes a powerful decision optimization tool in several areas. In order to contribute in this direction, we investigated the efficiency of c...
Conference Paper
Full-text available
This study aims to analyze the predictive performance of the univariate and forecasting combination approaches for GDP components. For the empirical results, were used quarterly data from the Brazilian economy between 1996 and 2020. The univariate evaluation used the model: a seasonal autoregressive integrated moving average, the Holt-Winters metho...
Conference Paper
Full-text available
Os indicadores de produção industrial são variáveis de interesse para a mensuração da atividade econômica de uma determinada região ou país e, assim, podem ser instrumentos de apoio à tomada de decisão para legisladores e agentes econômicos em geral. Desse modo, este trabalho propõe a utilização de três classes de modelos de previsão de séries temp...
Article
Full-text available
Forecasting the industry’s electricity consumption is essential for energy planning in a given country or region. Thus, this study aims to apply time-series forecasting models (statistical approach and artificial neural network approach) to the industrial electricity consumption in the Brazilian system. For the statistical approach, the Holt–Winter...
Technical Report
Full-text available
O ano de 2022 apontava para um cenário em que a pandemia parecia controlada, após dois anos de severa crise sanitária, mas suas consequências econômicas, sociais e sanitárias ainda se fariam sentir. A ampliação da cobertura vacinal, especialmente para os países pobres, a reorganização das cadeias de suprimento e o combate à inflação (que atingiu os...
Conference Paper
Full-text available
A finalidade deste artigo é contribuir para a formação de expectativas, por parte dos agentes econômicos, em relação ao comportamento futuro na economia brasileira. O estudo compara modelos de previsão de séries temporais aplicados aos valores do produto interno bruto trimestral entre os anos de 1996 e 2019. Dessa forma, os modelos selecionados for...

Questions

Question (1)
Question
Dear community,
I've started a study about banks' balance sheets and made a clustering through the variables, but I think that a Machine Learning method can result in evidence more useful. I don't found studies that make this kind of analysis and don't know the best approach for it.
If someone knows about references I will be grateful.
Thank you!

Network

Cited By

Projects

Projects (3)
Project
In this project, we propose a study on artificial intelligence models for forecasting electric energy consumption in the Brazilian industrial sector. In particular, the prediction models will be obtained based on Artificial Neural Networks and on Neuro-Fuzzy systems.
Project
The purpose of this research project is to produce two articles, both aiming to contribute to the academic and market debate concerning the empirical models applied to the forecast of economic and financial series. For the exposed purpose, the selected data was the exchange rate and the stock prices in the financial market.
Project
This project aims to contribute to the academic discussion on time series forecasting models applied to Brazilian GDP.