|
|
The use of artificial intelligence methods for time series prediction
Tripathi, Ankit
Financial market analysis and prediction have been topics of interest to traders and investors for decades. This thesis presents a comprehensive study on time series forecasting in the dynamic financial market of India, utilising a decade of historical data from Reliance Company's stock prices. The research encompasses three key components: bibliometric analysis for the domain globally, comparative evaluation of time series prediction methods in Indian markets, and implementation of a pre-processing approach incorporating economic factors on the selected models. Every section builds upon the collected information in the preceding section. The bibliometric analysis was used to establish an understanding of prevailing trends in time series forecasting techniques and answer relevant questions in the context of Indian markets to narrow down the scope of the study. This has been done by analysing 2202 documents ranging from the period of 1994-2023 consisting of articles, book chapter, review, book, note and letters in the English language only. The results help in the formation of a different perspective while understanding the overall intellectual landscape of the domain with subsections focusing on field leaders, author's productivity, uprise in domain based on publications and citations, the underlying pattern behind shifts in research areas based on authors keywords and publications that have impacted the domain significantly. The analysis extends beyond academic literature to include patents, providing a real-life state-of-the-art perspective. The results from bibliometrics have been used to select models for comparative analysis. The analysis assesses the performance of diverse time series prediction methods like deep learning algorithms (Long short-term memory model (LSTM)), traditional statistical models (Auto Regressive Integrated Moving Approach (ARIMA)), and advanced ensemble learning algorithms (XGBoost and FB-Prophet) using real-world data from the Indian financial market. The stock prices of Reliance Company serve as a case study, enabling a thorough evaluation of predictive accuracy and errors of the models. Simultaneously, a pre-processing approach has been proposed and implemented, integrating significant economic factors (Gold Price, USD to INR conversion, Consumer Price Index, Indian 10-year yield bond, and Wholesale Price Index) and evaluated with technical metrics (Mean squared error, Mean Absolute Error, R2 Score). The study investigates how the inclusion of these factors impacts prediction accuracy across the selected time series prediction methods. The comparative evaluation of models before and after the pre-processing method sheds light on the evolving predictive accuracy of LSTM, ARIMA, FB-Prophet, and XGBoost. This analysis provides valuable insights into the influence of economic factors on each method's performance. The study showed that the SARIMAX (extension of ARIMA with seasonality and exogenous factors) and XGBOOST performed relatively well with the proposed approach while LSTM with 80% training and FB prophet did not perform as expected in Indian financial markets. This research contributes to advancing the understanding of time series forecasting in the financial market of India, offering practical insights for decision-makers and researchers.
|
|
|
Assessment of informetric, bibliometric and scientometric methods as a tool for support and evaluation of research in European context
Boudová, Lucie ; Papík, Richard (advisor) ; Sklenák, Vilém (referee) ; Dvořák, Jan (referee)
This thesis is concerned with the topic of research evaluation by bibliometric methods at European level. European level is defined in two perspectives: first as a set of countries grouped in EU (and its historic predecessors), second the Framework Programmes were appointed as a representative of pan-European research. It is investigated how bibliometric methods are used in a research development and evaluation on both political and academic level. The thesis maps the history of use of bibliometric methods and indicators in great detail and it analyzes the aim and impact of such use. The rationale of use of those methods as well as the enablers such as availability of data are investigated. An experiment of constructing and analyzing the set of relevant data is pursued to assess the relevancy and feasibility of such analysis. Based on the findings the thesis summarizes the options and opportunities of bibliometrics as a method for formation and evaluation of European research.
|
|
|
Development of Bibliometrics in the Czech Republic
Dvořáková, Michaela ; Boudová, Lucie (advisor) ; Buřilová, Marcela (referee)
(in English) Bachelor thesis is focused on the development of bibliometrics in the Czech Republic which includes significant events, personalities and institutions which substantially related to the Czech bibliometrics. In the thesis bibliometrics is firstly defined as the science with its methods, laws and use. The general history of bibliometrics is also outlined for comparison with the Czech development. It describes the world development from the beginning to the present. History of the Czech bibliometrics presents similar description of history but in this case applied to the Czech scene. In detail the thesis focuses on probably the most famous Czech achievement from the field of bibliometrics. This is the scientometric working group founded by Jan Vlachý, world renowned Czech bibliometrician and scientometrician. In particular, we address to the group's activity and two preserved proceedings from organized seminars. Below the thesis emphasises the facts which still illustrate the situation in the field of the Czech bibliometrics. Specifically, it relates to the personalities of the Czech bibliometrics who in some way contributed to the development in this area and in this place the analyses of bibliometric literature of the Czech authors are also evaluated.
|
|
|
Scientometric research evaluation with focus on the Czech Republic
Troupová, Alžběta ; Souček, Martin (advisor) ; Boudová, Lucie (referee)
(in English) The master thesis is focused on the scientometric methods of research and development evaluation and their use in particular system applied in the Czech Republic. Its introductory part presents the field of scientometrics, scientometric and bibliometric indicators and citation indices. Chapter 7 deals with research and development evaluation in Czech Republic, especially with Research Evaluation Guidelines and describes its assesment rules, results and changes due to its annual actualization. A battle of wills between the Guidelines supporters and opponents is the topic of chapter 8, in particular in the context of reallocation of institutional funding according to the Guidelines. Ideas and opinions of prominent scientists and policymakers are being presented followed by brief treatise on Czech system of research and development evaluation audit carried out by the company Technopolis Limited. In the conclusion the author summarizes and debates positives and negatives of the Czech system of science evaluation.
|
|
| |
|
| |
|
|
From an institutional repository to the Base of Knowledge – case study
Kubrak, Weronika
The Warsaw University of Technology Base of Knowledge it is not only an institutional repository but also a good place to promote the scientific activities of the University staff. Unquestionable benefit of this Base is that it allows to present not only published papers but also collect e.g.: patents and projects documentations, professional activities of our staff and students dissertations. The paper presents the advantages of the system which combines functions of a repository and the Base of Knowledge functions.
Fulltext: idr-935_3 -  PDF
Slides: idr-935_1 - PDF; idr-935_2 - PDF
Video: idr-935_4 -  MP4
|
|
| |
|
| |
|
| |
guest ::
