[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120213-en":3,"doc-seo-120213-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120213,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Forecasting the Baltic Dry Sub-Indeces Using Machine Learning and Econometric Methods","This thesis evaluates a wide range of econometric and machine learning models for forecasting spot and forward indices in the Capesize, Panamax, and Supramax dry bulk shipping segments. Econometric methods include ARIMA, VAR, Bayesian VAR, and VECM, while machine learning models build multivariate predictors using MLP and LSTM. The study tests the impact of exogenous variables in selected VARX, MLP-X, and LSTM-X models, and also examines combined model strategies. Random Walk serves as a naive benchmark. Results show VECM performs best overall for spot rate forecasting, machine learning is less stable but captures correct rate direction, and no model outperforms Random Walk for forward rates.","Master’s thesis  \nNT NU  \nNorwegian Un iversity of Science and Technology  \nFaculty of Economics and Management Dept . of Industrial Economics and Technology Management  \nMarius Myrnes Bolstad Andreas Haugstvedt  \nForecasting the Baltic Dry SubIndeces Using  \nMachine Learning and Econometric Methods  \nMaster’s thesis in Industrial Economics and Technology Management  \nSupervisor: Sjur Westgaard  \nCo-supervisor: Morten Risstad June 2024  \nMarius Myrnes Bolstad Andreas Haugstvedt  \nForecasting the Baltic Dry Sub-Indeces Using  \nMachine Learning and Econometric Methods  \nMaster’s thesis in Industrial Economics and Technology Management Supervisor: Sjur Westgaard  \nCo-supervisor: Morten Risstad June 2024  \nNorwegian University of Science and Technology Faculty of Economics and Management  \nDept. of Industrial Economics and Technology Management  \nAbstract  \nThis thesis evaluates an extensive set of econometric and machine learning models for forecasting spot and forward indices in the Capesize, Panamax, and Supramax dry bulk shipping segments. We employ the econometric models ARIMA, VAR, Bayesian VAR, and VECM. Additionally, we construct multivariate predictors using the machine learning models Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) . Furthermore, we explore whether including exogenous variables in some selected models (VARX, MLP-X, LSTM-X), as well as combining different underlying models, improves the forecasting performance. Random Walk is used as a naive benchmark. We find that VECM is the best model overall to forecast spot rates. Machine learning models are less stable, but they are proficient at predicting the right direction of the rates. Combining econometric and machine learning models results in more stability and maintains good accuracy in predicting the direction. For forward rates, we find that no models beat the benchmark Random Walk.  \nPreface  \nThis thesis and the research conducted towards the final product represent the culmination of our paths towards attaining a Master of Science degree at the Norwegian University of Science and Technology. Here, we specialize in Financial Engineering at the Department of Industrial Economics and Technology Management, and this thesis reflects the knowledge gathered and skills honed throughout our studies. Work on this thesis was conducted from January to June 2024 .  \nWe conduct a comprehensive and thorough examination of the predictive capabilities of an extensive set of econometric and machine learning approaches aimed at the dry bulk industry. Market actors interested in the future development of freight rates, such as operators, vendors, brokers, and investors, should find this study relevant.  \nThroughout the work on this thesis, we utilized the online artificial intelligence service ChatGPT to aid in the modeling and writing processes and for online investigative purposes. The outputs generated by the service have been used with caution and care, and we have emphasized using them for tasks of a repetitive nature or when progress is halted. Thus, the service is a valuable aid toward the creation of this thesis.  \nAdditionally, we utilized the online grammar tool Grammarly to assist with the writing process. It’s important to emphasize that such tools should be used carefully and relied upon solely for correcting grammar and punctuation.  \nWe would like to thank our supervisor, Sjur Westgaard and our co-supervisor Morten Risstad, as well as Petter Eilif de Lange, Malvina Marchese and Amir Alizadeh. Their expertise and advice on academic writing, methodology, and potential investigative directions have been essential in completing this research. Additionally, we would like to thank the Head of Quantitative Strategy at Torvald Klaveness, Peter Lars Michael Lindstrøm, and the rest of the quantitative team, Oleg Kopylov and Ragnhild Noven, for their input and insights into the modeling of forecasting approaches for the dry bulk industry. All the individ","cbCaicg7L1G1nnMj","https://ap.wps.com/l/cbCaicg7L1G1nnMj","pdf",8501206,1,96,"English","en",105,"# Introduction\n## Literature Review\n## Data\n## Forecasting Models and Methodologies\n## Results","[{\"question\":\"Which econometric and machine learning models are evaluated for forecasting Baltic Dry spot and forward indices?\",\"answer\":\"The thesis evaluates ARIMA, VAR, Bayesian VAR, and VECM, alongside machine learning models MLP and LSTM. It also tests exogenous-variable versions such as VARX, MLP-X, and LSTM-X, plus combined model approaches.\"},{\"question\":\"How does VECM perform compared with other models for spot-rate forecasting?\",\"answer\":\"VECM is found to be the best overall model for forecasting spot rates in the studied dry bulk segments.\"},{\"question\":\"Do any models outperform the Random Walk benchmark for forward-rate forecasting?\",\"answer\":\"No models are found to beat the Random Walk benchmark for forward rates.\"}]","Forecasting the Baltic Dry Sub-Indeces Using Machine Learning and Econometric Methods | PDF",1785728756,242,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"forecasting-the-baltic-dry-sub-indeces-using-machine-learning-and-econometric-methods","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/forecasting-the-baltic-dry-sub-indeces-using-machine-learning-and-econometric-methods/120213/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Which econometric and machine learning models are evaluated for forecasting Baltic Dry spot and forward indices?","Question",{"text":76,"@type":77},"The thesis evaluates ARIMA, VAR, Bayesian VAR, and VECM, alongside machine learning models MLP and LSTM. It also tests exogenous-variable versions such as VARX, MLP-X, and LSTM-X, plus combined model approaches.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does VECM perform compared with other models for spot-rate forecasting?",{"text":81,"@type":77},"VECM is found to be the best overall model for forecasting spot rates in the studied dry bulk segments.",{"name":83,"@type":74,"acceptedAnswer":84},"Do any models outperform the Random Walk benchmark for forward-rate forecasting?",{"text":85,"@type":77},"No models are found to beat the Random Walk benchmark for forward rates.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]