[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128317-en":3,"doc-seo-128317-105":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},128317,962085564381,"Clementine","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Early-Stage Venture Financing - A Data-Driven Approach with Machine Learning Application - Doctor of Philosophy Thesis","Venture capital (VC) and private equity (PE) are central financial engines for economic and societal growth, yet private markets remain difficult to analyse due to information asymmetry, illiquidity, and moral hazard. This thesis investigates how alternative datasets and machine learning models can tackle valuation and investment-selection challenges. Using NLP to process unstructured text and signals from social media and financial news, the research supports tasks such as ICO token valuation, early-stage company assessment, and startup screening, benefiting both researchers and practitioners.","Early-Stage Venture Financing: A Data-Driven Approach with Machine Learning Application  \nPornpanit Rasivisuth  \nA dissertation submitted in partial fulfillment of the requirements for the degree of  \nDoctor of Philosophy  \nof  \nUniversity College London.  \nInstitute of Finance and Technology Department of Civil and Environmental Engineering University College London  \nJuly 3, 2025  \n2  \nI, Pornpanit Rasivisuth, confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I confirm that this has been indicated in the work.  \nAbstract  \nVenture capital (VC) and private equity (PE) become indispensable financial assets, globally driving economic and societal growth. This project primarily aims to investigate the utility of alternative datasets and machine learning models in addressing various challenges prevalent within private markets. These challenges, often exacerbated by the illiquid nature of private investments, information asymmetry, and potential moral hazard issues, include the valuation of Initial Coin O!ering (ICO) tokens, the assessment of early-stage company valuations, and the selection of startups for venture capital funds. A Natural Language Processing (NLP) model, capable of analysing unstructured text data, is employed alongside additional signals derived from alternative data sources such as social media and financial news. Overall, the project is anticipated to benefit academic researchers and practitioners within the private capital sectors, contributing to recent advancements in both the technology and sustainable finance domains.  \nImpact Statement  \nVenture capital, a cornerstone of the private capital market, focuses on investing in and supporting the growth of early-stage companies characterised by higher risk profiles, illiquidity, and long-term investment horizons. However, the process of assessing these entrepreneurial ventures is hindered by information asymmetries, moral hazard, and the limitations of traditional datasets. Moreover, the evolving landscape of technology, such as blockchain, and the growing emphasis on sustainable finance necessitate a re-evaluation of investment strategies. To address these challenges, this research introduces a novel approach that leverages alternative datasets and machine learning to enhance the screening and due diligence processes during the initial stages of private capital investment.  \nBy addressing the shortcomings of existing token rating methodologies and whitepaper analysis used in token financing for initial coin o!erings (ICOs), the first paper introduces an ML-based framework that leverages social media sentiment to predict token returns. The findings underscore the critical role of understanding market sentiment and investor behaviour through social media in shaping token return predictions and highlight the systemic risks inherent in the lightly regulated ICO market. These insights not only advance academic knowledge but also provide valuable guidance for practitioners and policymakers seeking to foster a more transparent and investor-centric token economy.  \nThe second study introduces a pioneering valuation framework for early-stage companies that surpasses traditional financial analysis by seamlessly integrating machine learning and sustainability data. Incorporating ESG indicators, the model provides a more comprehensive and forward-looking assessment of early-stage com-  \nImpact Statement 5  \npanies, demonstrating the value of alternative, unstructured datasets. This approach not only enhances investment decision-making but also aligns with growing investor demand for sustainable investments. Addressing the limitations of traditional valuation methods like discounted cash flow, which often rely on inaccessible financial statements, the study unveils the predictive power of a novel model to capture the complexities of early-stage companies. This significantly advances valuation theory and practice, fostering a ","cbCaigx38XpuU3SH","https://ap.wps.com/l/cbCaigx38XpuU3SH","pdf",4171666,1,277,"English","en",105,"# Abstract\n# Impact Statement\n## Token financing and social media sentiment\n## Early-stage valuation using ML and sustainability data\n## Reinforcement learning for venture capital recommendations\n# Acknowledgements","[{\"question\":\"What problem does this thesis address in private markets?\",\"answer\":\"It addresses valuation and screening challenges driven by illiquidity, information asymmetry, and moral hazard in private investments.\"},{\"question\":\"How does the research use machine learning and alternative data?\",\"answer\":\"It applies NLP to analyse unstructured text and combines it with alternative signals from social media and financial news to improve multiple decision tasks.\"},{\"question\":\"What are the main outcomes emphasized in the thesis impact statement?\",\"answer\":\"It highlights ML methods for ICO token return prediction, an ML plus ESG-driven valuation framework for early-stage firms, and a reinforcement learning recommendation system to improve venture capital investment decisions.\"}]","Early-Stage Venture Financing - A Data-Driven Approach with Machine Learning Application - Doctor of Philosophy Thesis | PDF",1785946804,698,{"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},"early-stage-venture-financing-a-data-driven-approach-with-machine-learning-application-doctor-of-philosophy-thesis","",{"@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/early-stage-venture-financing-a-data-driven-approach-with-machine-learning-application-doctor-of-philosophy-thesis/128317/",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","2026-08-23","2026-08-05",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},"What problem does this thesis address in private markets?","Question",{"text":76,"@type":77},"It addresses valuation and screening challenges driven by illiquidity, information asymmetry, and moral hazard in private investments.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the research use machine learning and alternative data?",{"text":81,"@type":77},"It applies NLP to analyse unstructured text and combines it with alternative signals from social media and financial news to improve multiple decision tasks.",{"name":83,"@type":74,"acceptedAnswer":84},"What are the main outcomes emphasized in the thesis impact statement?",{"text":85,"@type":77},"It highlights ML methods for ICO token return prediction, an ML plus ESG-driven valuation framework for early-stage firms, and a reinforcement learning recommendation system to improve venture capital investment decisions.","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"]