{"paper_id":"2408.09420","title":"Enhancing Startup Success Predictions in Venture Capital: A GraphRAG Augmented Multivariate Time Series Method","authors":["Zitian Gao","Yihao Xiao"],"paper_date":"2024-08-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2408.09420v5","page_url":"https://thequant.space/flowcharts/enhancing-startup-success-predictions-in-venture-capital-a/","scores":{"empirical_rigor":4,"math_complexity":6.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a GraphRAG‑augmented Seq2Seq multivariate time series method for predicting startup success in venture capital.","quote":"We propose a GraphRAG-enhanced multivariate Seq2Seq time series analysis method to predict startup success in the context of venture capital (VC).","summary":"In the Venture Capital (VC) industry, predicting the success of startups is challenging due to limited financial data and the need for subjective revenue forecasts. Previous methods based on time series analysis often fall short as they fail to incorporate crucial inter-company relationships such…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Model performance depends on high‑quality unstructured text data.","type":"data","stated":"implied","quote":"GraphRAG’s performance relies heavily on data quality, with high costs for processing unstructured text and computational challenges during indexing."},{"assumption":"Results are based on Chinese A‑share market companies and may not generalize to other markets.","type":"market","stated":"implied","quote":"The dataset used in this study is primarily focused on the Chinese A-share market, which may limit the generalizability of our findings."}]},"datasets":{"status":"available","items":[{"name":"BBT-FinCorpus","provider":"Lu et al. (2023)","kind":"text-news","access":"public","period":"approximately 20 years of historical dat","universe":null,"quote":"BBT-FinCorpus is a large‑scale Chinese financial corpus that includes approximately 300GB of raw text data gathered from four distinct sources: (1) financial, political, and economic news published by mainstream media platforms over the past 20 years; (2) all announcements and financial reports from publicly listed com"},{"name":"Wanjuan1.0","provider":"He et al. (2023)","kind":"text-news","access":"public","period":null,"universe":null,"quote":"The second part of the dataset comes from Wanjuan1.0, which includes 7 million news articles covering various fields across the Chinese internet."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The GraphRAG‑augmented Seq2Seq LSTM model outperforms all baselines, achieving about a 16% higher R‑squared than the best baseline.","kind":"performance","quote":"As shown in Table 1, our proposed GraphRAG augmented sequence-to-sequence LSTM method outperforms all baseline methods on this task. Specifically, we observed an approximately 16% improvement in R-squared compared to the best-performing model among the baselines."},{"finding":"Increasing the regularization strength to λ=10 yields the best predictive performance (R‑squared = 0.4075).","kind":"predictive-accuracy","quote":"Table 2: Effect of Regularization Strength λ (optimal 10) on MSE, MAE, and R-squared"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":43,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:03:51Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}