On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “Crunchbase”

Startup success prediction and VC portfolio simulation using CrunchBase datacs.LG

Predicting startup success using Crunchbase data and deep learning.

problem Predicting startup success in a volatile entrepreneurial ecosystem.

method Novel deep learning model integrating funding metrics, founder features, and industry category.

result Achieved 14 times capital growth and identified high-potential startups.

startup success Crunchbase deep learning machine learning venture capital

2023-09-27abs ↗pdf ↗

Measuring the performance of investments in information security startups: An empirical analysis by cybersecurity sectors using Crunchbase dataq-fin.PR

Study evaluates early-stage cybersecurity firms' performance using Crunchbase data.

problem Assessing performance of early-stage cybersecurity startups.

method Empirical analysis of 19 cybersecurity sectors using Crunchbase data.

result Significant variations in capital raised and post-money valuations across cybersecurity sectors.

cybersecurity startups investment performance Crunchbase data private equity funding rounds

2024-02-07abs ↗pdf ↗

Cryptocurrency co-investment network: token returns reflect investment patternsq-fin.ST

Study shows institutional investments significantly impact cryptocurrency market evolution.

problem Limited understanding of institutional investments' role in cryptocurrency market evolution.

method Quantitative analysis of 1324 cryptocurrencies' investments from 2014-2022.

result Institutional investments correlate with cryptocurrency market capitalization.

cryptocurrency institutional investments co-investment network market behavior hedge funds

2023-01-05abs ↗pdf ↗

The varying importance of extrinsic factors in the success of startup fundraising: competition at early-stage and networks at growth-stageq-fin.GN

We address the issue of the factors driving startup success in raising funds. Using the popular and public startup database Crunchbase, we explicitly take into account two extrinsic characteristics of startups: the competition that the companies face, using similarity measures derived from the Word2Vec algorithm, as we…

2019-06-07abs ↗pdf ↗

Machine learning-based similarity measure to forecast M&A from patent dataphysics.soc-ph

Mass algorithm predicts M&A deals from patent data.

problem Hard to automatically predict M&A deals due to complex human skills.

method Machine learning-based similarity measure (MASS) applied to patent data.

result MASS outperforms LightGCN in forecasting M&A deals.

Mergers and Acquisitions Machine Learning Patent Data Forecasting Interpretable Algorithm

2024-04-10abs ↗pdf ↗

Interpretable Machine Learning for Predicting Startup Funding, Patenting, and Exitscs.LG

Study predicts startup outcomes like funding, patenting, IPOs using machine learning.

problem Forecasting startup success metrics like funding, patenting, IPOs.

method Developed interpretable machine learning framework, used preprocessing, class imbalance handling, and compared multiple models.

result Achieved high AUROC values for patent, funding, and exit predictions.

startup machine learning funding patenting IPO

2025-10-10abs ↗pdf ↗

The Geoeconomics of Venture Capital An Economic Complexity Approach to Emerging Technological Sovereigntyecon.GN

Geoeconomic analysis of venture capital portfolios reveals key emerging tech domains and countries.

problem Quantifying geoeconomic power and technological sovereignty through venture capital data.

method Economic complexity methods applied to venture capital portfolios and RVA metrics.

result Cloud Computing, Cybersecurity Tools, and Medtech have the highest concentration of specialization among high-GCI countries.

venture capital economic complexity geoeconomics emerging tech technology sovereignty

2026-04-10abs ↗pdf ↗

PHBench: A Benchmark for Predicting Startup Series A Funding from Product Hunt Launch Signalsq-fin.PR

PHBench predicts Series A funding from Product Hunt launch signals with 7.8% accuracy.

problem Predicting startup Series A funding from launch signals on Product Hunt.

method Constructed PHBench from 67,292 Product Hunt posts, linked to funding records, and used a three-component ensemble model.

result Best-performing model achieved F0.5 = 0.097 and AP = 0.037, with a statistically significant advantage over logistic regression.

startup funding Product Hunt launch signals machine learning benchmark

2026-05-03abs ↗pdf ↗