{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:210643261"},"canonical_url":"https://search.dev.ndltd.org/etd/vilnius/oai:vu.lt:elaba:210643261","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Kredito ciklo prognozavimo modeliai Baltijos šalims /","abstract":"The aim of this thesis is to investigate the time series of the systematic risk factor in two sectors in the Baltic States and to develop appropriate forecasting models. Before using macroeconomic indicators in the analysis smoothed acceleration cycles were developed for them, i. e. the annual change in the data was calculated and the moving average method was applied for smoothing. The correlation analysis showed that systematic risk factor is most strongly correlated with different macroeconomic factors across countries while a large proportion of macroeconomic variables studied are strongly mutually correlated. Cross-correlation shows that systematic risk factor is more strongly correlated with previous values of some of the macroeconomic indicators. The baseline ARMA(2, 1) models without exogenous regressors were initially constructed to forecast the credit cycle. In some sectors the residuals of these models did not satisfy the assumptions of independence and/or normality, the models without regressors had relatively large errors in the testing set. While constructing regression with ARMA(2, 1) residuals models, two methods of taking COVID-19 pandemic impact on the systematic risk factor into account were considered – a binary variable with a value of 1 in the pandemic period, and detrending the systematic risk factor series during the COVID-19 period. In five out of the six segments, more accurate predictions were obtained using detrended time series. The most difficult model selection was for Estonian sector A data as the model’s residuals strongly violate the independence assumption in this sector, and some of the macroeconomic indicators in the model equation have different signs than those assumed by correlation. Models with regressors generally produced more accurate predictions. Although the errors in the predictions are still relatively big, most of the observed values of the systematic risk factor fall within the 95 % confidence intervals of the forecasts.","abstract_html":"The aim of this thesis is to investigate the time series of the systematic risk factor in two sectors in the Baltic States and to develop appropriate forecasting models. Before using macroeconomic indicators in the analysis smoothed acceleration cycles were developed for them, i. e. the annual change in the data was calculated and the moving average method was applied for smoothing. The correlation analysis showed that systematic risk factor is most strongly correlated with different macroeconomic factors across countries while a large proportion of macroeconomic variables studied are strongly mutually correlated. Cross-correlation shows that systematic risk factor is more strongly correlated with previous values of some of the macroeconomic indicators. The baseline ARMA(2, 1) models without exogenous regressors were initially constructed to forecast the credit cycle. In some sectors the residuals of these models did not satisfy the assumptions of independence and/or normality, the models without regressors had relatively large errors in the testing set. While constructing regression with ARMA(2, 1) residuals models, two methods of taking COVID-19 pandemic impact on the systematic risk factor into account were considered – a binary variable with a value of 1 in the pandemic period, and detrending the systematic risk factor series during the COVID-19 period. In five out of the six segments, more accurate predictions were obtained using detrended time series. The most difficult model selection was for Estonian sector A data as the model’s residuals strongly violate the independence assumption in this sector, and some of the macroeconomic indicators in the model equation have different signs than those assumed by correlation. Models with regressors generally produced more accurate predictions. Although the errors in the predictions are still relatively big, most of the observed values of the systematic risk factor fall within the 95 % confidence intervals of the forecasts.","abstract_has_math":false,"creators":["Bilaišis, Mantas,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-24T05:55:52Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD210643261&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Bilaišis, Mantas,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:210643261/210643261.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD210643261&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The aim of this thesis is to investigate the time series of the systematic risk factor in two sectors in the Baltic States and to develop appropriate forecasting models. Before using macroeconomic indicators in the analysis smoothed acceleration cycles were developed for them, i. e. the annual change in the data was calculated and the moving average method was applied for smoothing. The correlation analysis showed that systematic risk factor is most strongly correlated with different macroeconomic factors across countries while a large proportion of macroeconomic variables studied are strongly mutually correlated. Cross-correlation shows that systematic risk factor is more strongly correlated with previous values of some of the macroeconomic indicators. The baseline ARMA(2, 1) models without exogenous regressors were initially constructed to forecast the credit cycle. In some sectors the residuals of these models did not satisfy the assumptions of independence and/or normality, the models without regressors had relatively large errors in the testing set. While constructing regression with ARMA(2, 1) residuals models, two methods of taking COVID-19 pandemic impact on the systematic risk factor into account were considered – a binary variable with a value of 1 in the pandemic period, and detrending the systematic risk factor series during the COVID-19 period. In five out of the six segments, more accurate predictions were obtained using detrended time series. The most difficult model selection was for Estonian sector A data as the model’s residuals strongly violate the independence assumption in this sector, and some of the macroeconomic indicators in the model equation have different signs than those assumed by correlation. Models with regressors generally produced more accurate predictions. Although the errors in the predictions are still relatively big, most of the observed values of the systematic risk factor fall within the 95 % confidence intervals of the forecasts."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Kredito ciklo prognozavimo modeliai Baltijos šalims /","Credit cycle forecasting models for baltic countries."]}]}],"canonical_facts":{"dc:creator":["Bilaišis, Mantas,"],"dc:date":["2024"],"dc:description":["The aim of this thesis is to investigate the time series of the systematic risk factor in two sectors in the Baltic States and to develop appropriate forecasting models. Before using macroeconomic indicators in the analysis smoothed acceleration cycles were developed for them, i. e. the annual change in the data was calculated and the moving average method was applied for smoothing. The correlation analysis showed that systematic risk factor is most strongly correlated with different macroeconomic factors across countries while a large proportion of macroeconomic variables studied are strongly mutually correlated. Cross-correlation shows that systematic risk factor is more strongly correlated with previous values of some of the macroeconomic indicators. The baseline ARMA(2, 1) models without exogenous regressors were initially constructed to forecast the credit cycle. In some sectors the residuals of these models did not satisfy the assumptions of independence and/or normality, the models without regressors had relatively large errors in the testing set. While constructing regression with ARMA(2, 1) residuals models, two methods of taking COVID-19 pandemic impact on the systematic risk factor into account were considered – a binary variable with a value of 1 in the pandemic period, and detrending the systematic risk factor series during the COVID-19 period. In five out of the six segments, more accurate predictions were obtained using detrended time series. The most difficult model selection was for Estonian sector A data as the model’s residuals strongly violate the independence assumption in this sector, and some of the macroeconomic indicators in the model equation have different signs than those assumed by correlation. Models with regressors generally produced more accurate predictions. Although the errors in the predictions are still relatively big, most of the observed values of the systematic risk factor fall within the 95 % confidence intervals of the forecasts."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD210643261&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:210643261/210643261.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Kredito ciklo prognozavimo modeliai Baltijos šalims /","Credit cycle forecasting models for baltic countries."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-07-24T05:55:52Z"}