Scientists Develop AI to Predict the Success of Startup Companies

A study in which machine-learning models were trained to assess over 1 million companies has shown that artificial intelligence (AI) can accurately determine whether a startup firm will fail or become successful. The outcome is a tool that has the potential to help investors identify the next unicorn.

It is well known that around 90% of startups are unsuccessful: between 10% and 22% fail within their first year, and this presents a significant risk to Venture Capitalists and other investors in early-stage companies. In a bid to identify which companies are more likely to succeed, researchers have developed machine-learning models trained on the historical performance of over 1 million companies. Their results, published in KeAi’s The Journal of Finance and Data Science, show that these models can predict the outcome of a company with up to 90% accuracy. This means that potentially 9 out of 10 companies are correctly assessed.

"This research shows how ensembles of non-linear machine-learning models applied to big data have huge potential to map large feature sets to business outcomes, something that is unachievable with traditional linear regression models," explains co-author Sanjiv Das, Professor of Finance and Data Science at Santa Clara University's Leavey School of Business in the US.

The authors developed a novel ensemble of models in which the combined contribution of the models outweighs the predictive potential of each one alone. Each model classifies a company, placing it in one of several success categories or a failure category with a specific probability. For example, a company might be very likely to succeed if the ensemble says it has a 75% probability of being in the IPO (listed on the stock exchange) or 'acquired by another company' category, while only 25% of its prediction would fall into the failed category.

The researchers trained the models on data sourced from Crunchbase, a crowd-sourced platform containing detailed information on many companies. They married the Crunchbase observations with patent data from the USPTO (United States Patent and Trademark Office). Given the crowd-sourced nature of Crunchbase, it was no surprise to learn that some companies’ entries miss information. This observation inspired the authors to measure the amount of information missing for each company and use this value as an input to the model. This observation turned out to be one of the most critical features in determining whether a company would be acquired or otherwise fail.

Lead author Greg Ross of Venhound Inc. notes that the ensemble of models, along with novel data features, "generates a level of accuracy, precision and recall that exceeds other similar studies. Investors can use this to quickly evaluate prospects, raise potential red flags and make more informed decisions on the composition of their portfolios."

Greg Ross, Sanjiv Das, Daniel Sciro, Hussain Raza.
CapitalVX: A machine learning model for startup selection and exit prediction.
The Journal of Finance and Data Science, 2021. 10.1016/j.jfds.2021.04.001

Most Popular Now

Orion Health Supports Professional Recor…

Orion Health is supporting the Professional Record Standards Body's partnership scheme by applying to become a 'quality partner'. The company, which is one of the UK’s leading providers of shared care...

FDA Authorizes Software that Can Help Id…

Today, the U.S. Food and Drug Administration authorized marketing of software to assist medical professionals who examine body tissues (pathologists) in the detection of areas that are suspicious for cancer...

Northumbria Healthcare Picks CliniSys to…

Pathologists at one of England's most innovative trusts have chosen the CliniSys laboratory information system (LIMS) as part of a digital strategy to support its drive to continually improve patient...

Study Finds Telemedicine Appointments Re…

Telemedicine appointments combined with in-person visits significantly reduced the risk of further illness for children with medically complex cases, according to results of a new study by researchers with The...

Contact-Tracing Apps could Improve Vacci…

Mathematical modeling of disease spread suggests that herd immunity could be achieved with fewer vaccine doses by using Bluetooth-based contact-tracing apps to identify people who have more exposure to others...

A Computer Algorithm Called 'Eva' May Ha…

A prescriptive computer program developed by the USC Marshall School of Business and Wharton School of Business of the University of Pennsylvania for Greece to identify asymptomatic, infected travelers...

FDA Clears First Major Imaging Device Ad…

Today, the U.S. Food and Drug Administration cleared the first new major technological improvement for Computed Tomography (CT) imaging in nearly a decade. "Computed tomography is an important medical imaging tool...

Using Internet in Retirement Boosts Cogn…

Using the internet during your retirement years can boost your cognitive function, a new study has found. Researchers from Lancaster University Management School, the Norwegian University Science and Technology and...

AI Tool Improves Accuracy of Breast Canc…

A computer program trained to see patterns among thousands of breast ultrasound images can aid physicians in accurately diagnosing breast cancer, a new study shows. When tested separately on 44,755 already...

Study Shows Trust is still at Heart of N…

A new study has shown that issues surrounding trust are still at the heart of people's reluctance to download and use the NHS App, particularly among Black, Asian and minority...

Time until Dementia Symptoms Appear can …

Researchers at Washington University School of Medicine in St. Louis have developed an approach to estimating when a person who is likely to develop Alzheimer’s disease, but has no cognitive...