Thesis Details

Optimalizace strojového učení pro predikci KPI

Master's Thesis Student: Haris Daniel Academic Year: 2017/2018 Supervisor: Bartík Vladimír, Ing., Ph.D.
English title
Machine Learning Optimization of KPI Prediction
Language
Czech
Abstract

This thesis aims to optimize the machine learning algorithms for predicting KPI metrics for an organization. The organization is predicting whether projects meet planned deadlines of the last phase of development process using machine learning. The work focuses on the analysis of prediction models and sets the goal of selecting new candidate models for the prediction system. We have implemented a system that automatically selects the best feature variables for learning. Trained models were evaluated by several performance metrics and the best candidates were chosen for the prediction. Candidate models achieved higher accuracy, which means, that the prediction system provides more reliable responses. We suggested other improvements that could increase the accuracy of the forecast.

Keywords

software development, KPI, NPI, machine learning, preprocessing, cross-validation, classification, prediction, boosting, neural networks, ensemble, boosting, support vector machines, decision tree, random forest, naive bayes, performance metrics, ROC

Department
Degree Programme
Information Technology, Field of Study Information Systems
Files
Status
defended, grade A
Date
21 June 2018
Reviewer
Committee
Kreslíková Jitka, doc. RNDr., CSc. (DIFS FIT BUT), předseda
Lengál Ondřej, Ing., Ph.D. (DITS FIT BUT), člen
Matoušek Petr, doc. Ing., Ph.D., M.A. (DIFS FIT BUT), člen
Rychlý Marek, RNDr., Ph.D. (DIFS FIT BUT), člen
Smrčka Aleš, Ing., Ph.D. (DITS FIT BUT), člen
Šeda Miloš, prof. RNDr. Ing., Ph.D. (FME BUT), člen
Citation
HARIS, Daniel. Optimalizace strojového učení pro predikci KPI. Brno, 2018. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2018-06-21. Supervised by Bartík Vladimír. Available from: https://www-dev.fit.vutbr.cz/study/thesis/21142/
BibTeX
@mastersthesis{FITMT21142,
    author = "Daniel Haris",
    type = "Master's thesis",
    title = "Optimalizace strojov\'{e}ho u\v{c}en\'{i} pro predikci KPI",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2018,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/21142/"
}
Back to top