TSI logo 25 years
LV EN
Home > About Us > Structure and Government > Abstracts

DEGREE

PROGRAMME

FACULTY

YEAR

LANGUAGE

KEYWORDS

Application of machine learning in decision support system

The aim of the work is to improve the accuracy of predicting wait times in an existing queue management system using machine learning. Client-provided data was analyzed, and models were trained using various machine learning algorithms. Performance measures of the models were collected, and the best one was selected. Additionally, software and a database were developed to manage the training process and evaluate the quality of the models. The quality of the software was assessed using industry-standard methodologies and tested.

Author: Jevgēnijs Nikolajevs

Supervisor: Jeļena Kijonoka

Degree: Bachelor

Year: 2024

Work Language: Latvian

Study programme: Computer Science

More...

Development of a personal financial management application

Nowadays, financial management is essential in people's lives, as price increases and economic instability require more careful planning of personal finances. Technological development makes this process accessible to everyone, offering various expenditure tracking and budget planning solutions. In the bachelor's thesis, the most popular financial management applications were reviewed, showing that although they offer an intuitive interface and automated budget functions, they also have shortcomings.The goal of the work is to create an application that provides a convenient and digitally enhanced tool for financial planning and tracking. To achieve the goal, tasks included reviewing similar applications, defining requirements, creating the interface and database, developing transaction management and budgeting functionality, and testing the application. All tasks were fully completed.The application uses Python and Flask, SQLite database, HTML, CSS, and JavaScript. As a result, an application with a clear interface was developed, providing manual transaction entry and bank account Excel format upload, editing, and deletion, as well as budget control and transaction visualizations. These functions help users manage their finances more effectively and make better decisions.

Author: Jūlija Ivčenkova

Supervisor: Olga Dribeņeca

Degree: Bachelor

Year: 2024

Work Language: Latvian

Study programme: Computer Science

More...

Development of Project Management Assistance Software Enhanced with Generative AI Technologies.

This thesis explores the practical value of applying Generative Artificial Intelligence in project management software to enhance a manager's work. The aim is to evaluate the efficiency and impact of GenAI on project management processes. The research begins with a review of existing academic and industry literature on integrating AI in project management. This is followed by detailed case study analyses of instances where AI has been integrated into project management tools. The Software Development Life Cycle methodology is used to develop and test the software, incorporating a prototyping phase to explore and validate concepts before full-scale development.The results of this study include creating a GenAI-powered software that significantly speeds up the staff selection process for projects by matching project requirements with personnel skills. The findings indicate that the developed software effectively leverages GenAI technologies to enhance the project management process, simplify managerial tasks and contribute to more efficient and accurate decision-making processes. This research highlights the potential of GenAI to transform project management practices and drive future innovations.

Author: Pāvels Kulajevs

Supervisor: Aleksejs Vesjolijs

Degree: Bachelor

Year: 2024

Work Language: Latvian

Study programme: Computer Science

More...

Development of a Cryptocurrency Trading Bot using AWS
Cloud Solutions

This bachelor thesis focuses on developing an automated trading bot for the cryptocurrency market. The goal is to create a cryptocurrency trading bot using of the Mean Reversion strategy and implement Cloud Solutions and Binance crypto exchange support.The process of development included establishing AWS infrastructure, such as EC2 instances, API Gateway, and Nginx, for hosting the bot. The bot's design is made up of separate modules that can be easily expanded allowing for adding the support of other crypto exchanges. As the result, the bot uses mean reversion algorithm on user chosen trading pairs, and places the order to sell or buy according to the algorithm decision. Moreover, it uses Binance API to access and manage user's cryptocurrencies.The bot was successfully tested in a real trading environment and proved to increase initial capital and manage risks. This thesis showcases the possibilities of combining

Author: Ēriks Mašinskis

Supervisor: Karina Kostjkina

Degree: Bachelor

Year: 2024

Work Language: English

Study programme: Computer Science

More...

Table View
Text View