[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290239-105":59,"doc-detail-290239-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","do-machine-learning-techniques-outperform-autoregressive-distributed-lag-models-in-inflation-forecasting-abstract","Do Machine Learning Techniques Outperform Autoregressive Distributed Lag Models in Inflation Forecasting? - Abstract","","Following the COVID-19 pandemic, Romania and other Central and Eastern European countries experienced very high inflation, making accurate short-term forecasts essential for monetary policy. The study compares modern machine learning methods (LSTM, Random Forests, SVR) with traditional Autoregressive Distributed Lag models for forecasting the Harmonised Index of Consumer Prices. It uses quarterly Romanian data (2006Q1–2023Q4) and monthly data for nine CEE economies (2006M1–2025M3), adding unemployment and sentiment indicators from central-bank reports and the European Commission’s Economic Sentiment Indicator.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/do-machine-learning-techniques-outperform-autoregressive-distributed-lag-models-in-inflation-forecasting-abstract/290239/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/do-machine-learning-techniques-outperform-autoregressive-distributed-lag-models-in-inflation-forecasting-abstract/290239.png","ImageObject",300,407,{"name":92,"@type":93},"Finn","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-05","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Which models are compared for inflation forecasting in the study?","Question",{"text":113,"@type":114},"The paper compares LSTM, Random Forests, and Support Vector Regression against traditional Autoregressive Distributed Lag (ARDL) models for forecasting inflation.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What data and indicators are used to build the forecasting models?",{"text":118,"@type":114},"It uses quarterly data for Romania and monthly data for nine CEE economies, incorporating unemployment and sentiment indicators from central-bank reports and the European Commission’s Economic Sentiment Indicator.",{"name":120,"@type":111,"acceptedAnswer":121},"What evaluation scenarios are used to test model performance?",{"text":122,"@type":114},"Model performance is assessed with simulation experiments including high persistence, moving-average non-invertibility, nonlinear regimes, and structural breaks.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290239,1789641049,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},34359740700684,"https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487","Do Machine Learning Techniques Outperform Autoregressive Distributed Lag Models in Inflation Forecasting?  \nBogdan Oancea  , Mihae la Simionescu  , Richard Pospisil   \nBogdan Oancea, Department of Applied Economics and Quantitative Analysis, University of Bucharest, Bd. Regina Elisabeta no. 4–12, Sector 3, 030108 Bucharest, Romania, National Institute of Research and Development for Biological Sciences, Splaiul Independenței 296, 060031 Bucharest, Romania, [E-mail: bogdan.oancea@faa.unibuc.ro](E-mail: bogdan.oancea@faa.unibuc.ro), [bogdan.oancea@incdsb.ro](bogdan.oancea@incdsb.ro)  \nMihaela Simionescu, Department of Applied Economics and Quantitative Analysis, University of Bucharest, Bd. Regina Elisabeta no. 4–12, Sector 3, 030108 Bucharest, Romania, Institute for Economic Forecasting, Romanian Academy, Bucharest, Romania, Academy of Romanian Scientists, Ilfov 3, 050044 Bucharest, Romania, [E-mail: mihaela.simionescu@faa.unibuc.ro](E-mail: mihaela.simionescu@faa.unibuc.ro)  \n[Richard Pospisil](Richard Pospisil) ([Corresponding author](Corresponding author)), Tomas Bata University in Zlin, Faculty of Logistics & Crisis Management, Zlin, Czech Republic, E-mail: [r1pospisil@utb.cz](r1pospisil@utb.cz)  \nAbstract:  \nFollowing the COVID-19 pandemic, Romania and other Central and Eastern European (CEE) countries faced some of the highest inflation rates in the European Union, creating a pressing need for accurate short-term forecasts to guide monetary policy. This study compares modern machine learning (ML) methods - Long Short-Term Memory (LSTM) neural networks, Random Forests (RF) and Support Vector Regression (SVR) -with traditional Autoregressive Distributed Lag (ARDL) models in forecasting Harmonised Index of Consumer Prices. Using quarterly data for Romania (2006Q1–2023Q4) and monthly data for nine CEE economies (2006M1–2025M3), we incorporate unemployment and sentiment indicators derived from the Romanian Central Bank reports and the European Commission’s Economic Sentiment Indicator (ESI) . We further evaluate model performance through simulation experiments that include high persistence, moving-average non-invertibility, nonlinear regimes, and structural breaks. Across both empirical and LSTM and SVR models - they frequently deliver lower forecast errors than ARDL, with LSTM achieving up to 53% reductions in mean squared error relative to naïve benchmarks. However, ARDL remains competitive when sentiment indices  \nCopyright: © 2025 by the author(s). Licensee Prague University of Economics and Business, Czech Republic 495  \nare the main predictor. These findings highlight that while advanced ML models can capture nonlinear dynamics and regime changes, traditional econometric tools still provide valuable robustness, particularly in sentiment-driven contexts. Overall, integrating ML, econometric approaches, and sentiment analysis offers a more reliable toolkit for short-horizon inflation forecasting under economic uncertainty.  \nKeywords: Inflation, Long Short-Term Memory neural networks, Random Forests, Support Vector Regression, Autoregressive Distributed Lag models.  \nJEL classification: C51, C53, E31  \n1. Introduction  \nThis paper investigates whether modern machine-learning (ML) methods, specifically Long Short-Term Memory neural networks (LSTM), Random Forests (RF), and Support Vector Regression (SVR), can produce more accurate short-term inflation forecasts than traditional Autoregressive Distributed Lag (ARDL) models, especially during periods of high volatility and policy uncertainty. Focusing on Romania and the Central and Eastern European (CEE) economies after the COVID-19 pandemic, we developed and compared forecasting models that incorporate macroeconomic variables such as Harmonised Indices of Consumer Prices (HICP) as a proxy for inflation and unemployment, along with sentiment indicators derived from central-bank reports and the European Commission’s Economic Sentiment Indicator (ESI) . Our results highlight th","cbCaia2fZACTMuvm","https://ap.wps.com/l/cbCaia2fZACTMuvm","pdf",1576106,64,"English","# Abstract\n# Introduction\n## Research aim and model comparison\n## Motivation: post-COVID inflation in Romania","[{\"question\":\"Which models are compared for inflation forecasting in the study?\",\"answer\":\"The paper compares LSTM, Random Forests, and Support Vector Regression against traditional Autoregressive Distributed Lag (ARDL) models for forecasting inflation.\"},{\"question\":\"What data and indicators are used to build the forecasting models?\",\"answer\":\"It uses quarterly data for Romania and monthly data for nine CEE economies, incorporating unemployment and sentiment indicators from central-bank reports and the European Commission’s Economic Sentiment Indicator.\"},{\"question\":\"What evaluation scenarios are used to test model performance?\",\"answer\":\"Model performance is assessed with simulation experiments including high persistence, moving-average non-invertibility, nonlinear regimes, and structural breaks.\"}]","Do Machine Learning Techniques Outperform Autoregressive Distributed Lag Models in Inflation Forecasting? - Abstract | PDF",161]