[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290668-105":59,"doc-detail-290668-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","leveraging-machine-learning-for-australian-macroeconomic-forecasting","Leveraging machine learning for Australian macroeconomic forecasting","","Macroeconomic forecasting has traditionally relied on regression and time series methods, which often struggle to beat simple benchmarks. This study evaluates machine learning (ML) and deep learning (DL) approaches for forecasting key Australian macroeconomic indicators: GDP growth, CPI inflation, and the Interbank Overnight Cash Rate. A dataset from 1985–2023 with 16 literature-derived predictors is used to compare traditional models against ensemble learners and neural approaches.",{"@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/leveraging-machine-learning-for-australian-macroeconomic-forecasting/290668/",{"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/leveraging-machine-learning-for-australian-macroeconomic-forecasting/290668.png","ImageObject",300,407,{"name":92,"@type":93},"Levi","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-28","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Which Australian macroeconomic indicators are forecast in the study?","Question",{"text":113,"@type":114},"The study forecasts GDP growth, CPI inflation, and the Interbank Overnight Cash Rate for Australia.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What models are compared in the method section?",{"text":118,"@type":114},"The comparison includes benchmark approaches like random walk and ARIMAX, ensemble methods such as Random Forest and XGBoost, and deep learning models including LSTM, feedforward neural networks, and CNN-LSTM.",{"name":120,"@type":111,"acceptedAnswer":121},"What dataset size and predictor setup are used?",{"text":122,"@type":114},"The analysis uses data spanning 1985 to 2023 and incorporates 16 predictors selected from prior literature.","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},290668,1790571104,{"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":145,"read_time":146,"preview_page_count":4},7971461740909,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Proc. ANZIAM 66 (CTAC2024) pp. C167–C192, 2026 C167  \nLeveraging machine learning for Australian macroeconomic forecasting  \nBoyuan Li 1 Zihui Deng2 Gaurav Gupta3  \nYingxi Chen4  \n(Received 2 March 2025; revised 18 October 2025)  \nAbstract  \nMacroeconomic forecasting has traditionally relied on regression and time series methods, which have often struggled to outperform basic benchmarks. In this study, we explore the use of machine learning (ml) and deep learning (dl) techniques to forecast key macroeconomic indicators for Australia, specifically focusing on Gross Domestic Product growth, Consumer Price Index inflation, and the Interbank Overnight Cash Rate. Using a comprehensive dataset spanning from 1985 to 2023, we incorporate 16 predictors identified from previous literature. Our findings indicate that ml methods, particularly ensemble approaches such as Random Forest and xgboost, deliver superior predictive performance compared to traditional time series models and  \ndoi:10.21914/anziamproc.v66.19641, © Austral. Mathematical Soc. 2026. Published 2026-04-07, as part of the Proceedings of the 22nd Biennial Computational Techniques and Applications Conference. issn 1445-8810. (Print two pages per sheet of paper.) Copies of this article must not be made otherwise available on the internet; instead link directly to the doi for this article.  \nContents C168  \ndl methods. Although dl models such as Long Short-Term Memory (lstm) and Convolutional Neural Network-lstm were also tested, they did not achieve comparable accuracy in this context, highlighting the effectiveness of density-based ml approaches for macroeconomic forecasting.  \nContents  \n1 Introduction C168  \n2 Method C170  \n2. 1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . C171  \n2.2 Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C171  \n2.2. 1 Random walk . . . . . . . . . . . . . . . . . . . . . C171  \n2.2.2 ARIMAX . . . . . . . . . . . . . . . . . . . . . . . C173  \n2.2.3 Random forest . . . . . . . . . . . . . . . . . . . . C173  \n2.2.4 eXtreme gradient boosting (XGBoost) ....... C174  \n2.2.5 Long short-term memory ............... C175  \n2.2.6 Feedforward neural network . . . . . . . . . . . . . C177  \n2.2.7 CNN-LSTM . . . . . . . . . . . . . . . . . . . . . . C177  \n2.2.8 Ensemble model . . . . . . . . . . . . . . . . . . . . C178  \n2.3 Evaluation indicators . . . . . . . . . . . . . . . . . . . . . C178  \n3 Result C179  \n3.1 Model configuration ...................... C184  \n4 Discussion C184  \n4.1 Ablation attempt ....................... C187  \n1 Introduction  \nMacroeconomic forecasting is essential in macroeconomic policies development as it provides essential input for forward-looking policy deliberations [7] .  \n1 Introduction C169  \nHowever, macroeconomic data is often characterised by low serial correlation, high volatility, or structural changes, which make it hard to predict [5] .  \nForecasting models that have become widely used since the 1960s, such as econometric models [3 , 10], input–output models [17 , 28], and dynamic systems [15], were later shown to have incorrect economic predictions [14] . According to Fildes and Stekler [11], such forecasting models struggle with precision in critical areas. Notably, they tend to perform poorly in forecasting economic downturns and peaks, and they are often unable to assess inflation trends accurately. Diebold [9] explained that the failure of large-scale Keynesian frameworks to account for structural changes in the economy weakened their forecasting ability, and emphasized that the limitations posed by the assumption of stable relationships between economic variables often broke down during periods of rapid economic change. Unstructured methods such as Vector Autoregressive (var ) Dynamic Stochastic General Equilibrium (dsge), and Autoregressive Moving Average (arma) models have been proven to be more flexible and promising in capturing the dynamic characteristics of economic s","cbCaitWTrv37nV3T","https://ap.wps.com/l/cbCaitWTrv37nV3T","pdf",600091,26,"English","# Abstract\n# 1 Introduction\n# 2 Method\n## 2.1 Dataset\n## 2.2 Models\n## 2.3 Evaluation indicators\n# 3 Result\n## 3.1 Model configuration\n# 4 Discussion\n## 4.1 Ablation attempt","[{\"question\":\"Which Australian macroeconomic indicators are forecast in the study?\",\"answer\":\"The study forecasts GDP growth, CPI inflation, and the Interbank Overnight Cash Rate for Australia.\"},{\"question\":\"What models are compared in the method section?\",\"answer\":\"The comparison includes benchmark approaches like random walk and ARIMAX, ensemble methods such as Random Forest and XGBoost, and deep learning models including LSTM, feedforward neural networks, and CNN-LSTM.\"},{\"question\":\"What dataset size and predictor setup are used?\",\"answer\":\"The analysis uses data spanning 1985 to 2023 and incorporates 16 predictors selected from prior literature.\"}]","Leveraging machine learning for Australian macroeconomic forecasting | PDF",1789642330,66]