[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-564161-105":59,"doc-detail-564161-en":134},{"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":127,"head_meta":129,"extra_data":131,"updated_unix":133},105,"en","ai-driven-decision-support-system-for-construction-cost-forecasting-and-consultation-using-optimized-deep-learning-and-language-models-extended-long-short-term-memory-xlstm-with-pilgrimage-walk-optimization-pwo-and-qlora-sentiment","AI-driven decision support system for construction cost forecasting and consultation using optimized deep learning and language models - Extended Long Short-Term Memory (xLSTM) with Pilgrimage Walk Optimization (PWO) and QLORA sentiment","","Fluctuations in construction material prices significantly disrupt project budgets and bidding strategies through the Construction Cost Index (CCI). The paper presents an AI-driven decision-support system that forecasts CCI by integrating deep learning with Large Language Models and by translating textual signals into sentiment inputs. A multi-source framework fuses historical CCI records, macroeconomic indicators, and sentiment extracted from Traditional Chinese construction news. Time-series prediction uses an xLSTM network and sentiment models fine-tuned via QLORA, with hyperparameters optimized by PWO for short- and medium-term horizons. Experimental results show improved accuracy, and the deployed platform offers interpretable retrieval-augmented consultation for construction cost control and decision-making.",{"@graph":69,"@context":126},[70,84,105],{"@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/ai-driven-decision-support-system-for-construction-cost-forecasting-and-consultation-using-optimized-deep-learning-and-language-models-extended-long-short-term-memory-xlstm-with-pilgrimage-walk-optimization-pwo-and-qlora-sentiment/564161/",{"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/ai-driven-decision-support-system-for-construction-cost-forecasting-and-consultation-using-optimized-deep-learning-and-language-models-extended-long-short-term-memory-xlstm-with-pilgrimage-walk-optimization-pwo-and-qlora-sentiment/564161.png","ImageObject",300,407,{"name":92,"@type":93},"Connor ","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-16","2026-10-12",true,{"@type":102,"interactionType":103,"userInteractionCount":29},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the paper address in construction cost forecasting?","Question",{"text":112,"@type":113},"It targets inaccurate CCI forecasting caused by material price fluctuations and the underuse of sector-specific signals contained in construction-related news and policy text.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed system combine numerical and textual information?",{"text":117,"@type":113},"It uses a multi-source data framework that merges historical CCI and macroeconomic indicators with sentiment extracted from Traditional Chinese construction news, then feeds signals into both time-series forecasting and LLM-based components.",{"name":119,"@type":110,"acceptedAnswer":120},"Which methods are used for forecasting and model tuning?",{"text":121,"@type":113},"Time-series forecasting relies on an Extended Long Short-Term Memory (xLSTM) network, sentiment models are fine-tuned with Quantized Low-Rank Adaptation (QLoRA), and hyperparameters for both parts are optimized using Pilgrimage Walk Optimization (PWO).",{"name":123,"@type":110,"acceptedAnswer":124},"What benefits does the system provide for construction management?",{"text":125,"@type":113},"It improves forecasting accuracy by integrating sentiment features and PWO-tuned configurations, and it supports retrieval-augmented consultation with interpretable outputs to enhance cost control and bidding decisions.","https://schema.org",{"og:url":83,"og:type":128,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":130,"canonical":83},"index,follow",{"doc_id":132,"site_id":62},564161,1792211354,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":29,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":46,"language":143,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":144,"faqs":145,"seo_title":146,"seo_description":67,"update_tm":147,"read_time":31,"preview_page_count":19,"preview_urls":148},687207022233,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Automation in Construction 183 (2026) 106797  \nContents lists available at ScienceDirect  \nAutomation in Construction  \njournal [homepage:](homepage: www.elsevier.com/locate/autcon)[ www.elsevier.com/locate/autcon](homepage: www.elsevier.com/locate/autcon)  \n| AI-driven decision support system for construction cost forecasting and consultation using optimized deep learning and language models |  |  | |\n| --- | --- | --- | --- |\n| *\u003Cbr>Jui-Sheng Chou , Mei-Yuan Lin , Nguyen-Ngan-Hanh Pham\u003Cbr>National Taiwan University of Science and Technology, Taipei, Taiwan |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Construction cost index (CCI)\u003Cbr>Large language models (LLMs) Sentiment analysis\u003Cbr>Deep learning (DL)\u003Cbr>Time-series forecasting\u003Cbr>Pilgrimage walk optimization (PWO) Decision support system Construction informatics |  | Fluctuations in construction material prices significantly affect project budgets and bidding strategies via the Construction Cost Index (CCI). This paper develops an AI-driven decision-support system for construction cost forecasting and consultation, integrating deep learning and Large Language Models (LLMs) to enable intelligent CCI prediction. A multi-source data framework combines historical CCI records, macroeconomic indicators, and sentiment extracted from Traditional Chinese construction news. Time-series forecasting employs an Extended Long Short-Term Memory (xLSTM) network, while sentiment models are fine-tuned using Quantized Low-Rank Adaptation (QLoRA). Model hyperparameters for both the QLoRA-fine-tuned LLMs and the xLSTM forecasting models are optimized via the Pilgrimage Walk Optimization (PWO) algorithm, yielding two horizon-specific configurations for short- and medium-term forecasting. Experimental results demonstrate that integrating sentiment features and PWO-based tuning consistently improves forecasting accuracy relative to baseline models. The deployed platform integrates CCI forecasting, sentiment analytics, and retrieval-augmented consultation to provide interpretable forecasts that enhance cost control and decision-making in construction management. |  |\n\n1. Introduction  \nIn the construction industry, resource costs—including materials, labor, and equipment—constitute the largest share of total project expenditures. Among these, fluctuations in material prices are a primary cause of cost overruns [1]. Given the long lifecycles and resourceintensive nature of construction projects, such volatility can markedly affect both the profitability of ongoing works and the pricing strategies adopted during bidding. The Construction Cost Index (CCI) is a key indicator of overall cost trends and is routinely consulted by contractors during bid preparation to account for expected cost escalation [2]. Therefore, accurate forecasting of CCI trends is essential to improve cost control, enhance bidding competitiveness, and support long-term financial planning.  \nIn Taiwan, where natural resources are limited and most essential construction materials are imported, the CCI is particularly sensitive to international market dynamics. Global economic cycles, geopolitical tensions, and exchange rate fluctuations further complicate cost predictions [3]. Despite the growing need for timely cost intelligence, the Taiwanese construction sector continues to face data-related challenges. Government-published pricing information is released only monthly and  \nwith significant delay, whereas relevant market information is disseminated through financial news, industry reports, and policy announcements. The manual synthesis of such fragmented textual information is time-consuming and increases the risk of overlooking critical signals that influence material price trends.  \nWith the expansion of digital communication channels, marketrelated information now emerges from online news platforms, social media, and other real-time information streams. Although rich and immediate, these unstruc","cbCaiuxfGMp3AXOq","https://ap.wps.com/l/cbCaiuxfGMp3AXOq","pdf",10874898,"English","# Introduction\n## Construction cost volatility and the role of CCI\n## Data challenges in Taiwan and the need for timely intelligence\n## AI opportunities from unstructured real-time information\n## Limitations of existing CCI forecasting and research motivation","[{\"question\":\"What problem does the paper address in construction cost forecasting?\",\"answer\":\"It targets inaccurate CCI forecasting caused by material price fluctuations and the underuse of sector-specific signals contained in construction-related news and policy text.\"},{\"question\":\"How does the proposed system combine numerical and textual information?\",\"answer\":\"It uses a multi-source data framework that merges historical CCI and macroeconomic indicators with sentiment extracted from Traditional Chinese construction news, then feeds signals into both time-series forecasting and LLM-based components.\"},{\"question\":\"Which methods are used for forecasting and model tuning?\",\"answer\":\"Time-series forecasting relies on an Extended Long Short-Term Memory (xLSTM) network, sentiment models are fine-tuned with Quantized Low-Rank Adaptation (QLoRA), and hyperparameters for both parts are optimized using Pilgrimage Walk Optimization (PWO).\"},{\"question\":\"What benefits does the system provide for construction management?\",\"answer\":\"It improves forecasting accuracy by integrating sentiment features and PWO-tuned configurations, and it supports retrieval-augmented consultation with interpretable outputs to enhance cost control and bidding decisions.\"}]","AI-driven decision support system for construction cost forecasting and consultation using optimized deep learning and language models - Extended Long Short-Term Memory (xLSTM) with Pilgrimage Walk Optimization (PWO) and QLORA sentiment | PDF",1791840664,[149,153,157,161],{"page_no":8,"url":150,"width":151,"height":152},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-18/979964325ff545d17764eab33861c4fc.webp",983,1310,{"page_no":14,"url":154,"width":155,"height":156},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-18/2440794685235698629e409f9e42ac6c.webp",982,1309,{"page_no":81,"url":158,"width":159,"height":160},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-18/beb0d79604c1ac27e20651f72615f290.webp",981,1308,{"page_no":19,"url":162,"width":163,"height":164},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-18/0a3956d95c2847be6f195e60e94efc06.webp",980,1306]