EnglishPortugueseSpanish

MACHINE LEARNING WITH ARTIFICIAL NEURAL NETWORKS: A CASE STUDY OF STOCK QUOTATION FORECASTS AND REAL ESTATE FUNDS

Project summary

The modeling of time series shows itself as one of the main lines of action of computational statistics, being useful for decision support in different areas of knowledge and commonly present in information systems. Currently, there is a large amount of work dedicated to the study of new modeling alternatives or even to the comparison between the alternatives. In this sense, it has been common to direct computational resources to identify the best models. As an alternative to this movement, one can mention the methods aimed at model uncertainty. In fact, much of the time series literature implicitly assumes that there is a single model intrinsic to the series. However, it is worth emphasizing that even considering the existence of a single model, it will rarely be known a priori and there will be no guarantee that it will be selected as the best one to fit the observed series. Authors also comment that the adoption of a single model can lead to statistical biases and the underestimation of the real uncertainty underlying the time series. With these arguments in mind, model uncertainty seems to play an indispensable role in the analysis of time series. In this context, the main characteristics and basic properties of this problem will be presented. Some of the main time series prediction methods present in the literature will be described as artificial neural networks, for example. The proposal of individual models presented in this project will be developed using the artificial intelligence technique known as artificial neural networks, in addition to these, the experiments in this study will be conducted using the combined model that uses simple arithmetic mean to perform the aggregation of individual predictions. The experiments in this project will be conducted using a real-world time series that observes the growth of fish, and financial series that encompass stocks and real estate funds on the São Paulo stock exchange. The quality of these predictions obtained by the models will be measured through the metrics established in the literature as mean square error and mean absolute error.

Students

Hortência Bianca Dias
Mayara Fernanda de Oliveira Arruda

Guidance counsellors

Ricardo Tavares Antunes de Oliveira

Institution

Federal Institute of Mato Grosso do Sul
Cushion /
  MS -
  Brazil

Popular vote*

Did you like it? So vote and share now:

8+

Leave your comment

What did you think of this project? Participate by leaving your comment below:

Subscribe now
Notify of
guest
0 Comments
Inline feedback
View all comments

Popular vote*

Did you like it? So vote and share now:

8+

Students

Hortência Bianca Dias
Mayara Fernanda de Oliveira Arruda

Guidance counsellors

Ricardo Tavares Antunes de Oliveira

Institution

Instituto Federal de Mato Grosso do Sul
  MS –
  Brasil

Educational Incentives and Awards Offered

Research Areas

Get to know the projects that are competing in all of Mostratec Virtual's research areas:

Cellular and Molecular Biology and Microbiology
Biochemistry and Chemistry
Environmental Sciences
Animal and Plant Sciences
Computer Science
Planetary and Earth Sciences and Mathematics and Physics
Health Sciences
Education and Humanities
Environmental and Sanitary Engineering
Engineering and Materials
Electrical engineering
Electronic Engineering
Mechanical Engineering
History and Social Sciences
0
Click to leave your comment and participate!x
()
x

Popular Jury Awards

For the People's Jury awards, only single votes (one per user) and that are cast between 0/00 and 26:10 on 23/59 will be considered valid.

Entrepreneur Profile Test

Fill in your details below to perform your test: