Ivo Kolarov

Jun 17, 2024 | insight.factset.com | Lucy Tancredi |FactSet Insight |Yogendra Miraje |Ivo Kolarov

AI Strategies Series: 7 Ways to Overcome Hallucinations June 17, 2024 Hallucinations are perhaps the most important limitation of generative AI to stem. This article—the second in our six-part series... By Lucy Tancredi  |  Data Science and AI Read more June 17, 2024 AI Strategies Series: 7 Ways to Overcome Hallucinations Hallucinations are perhaps the most important limitation of generative AI to stem.

Mar 12, 2024 | insight.factset.com | FactSet Insight |Lucy Tancredi |Ivo Kolarov

Amid the hundreds of earnings calls and transcripts every quarter, our clients know there are valuable investment insights to be discovered. To significantly accelerate the process for them, we released Transcript Assistant, our first interactive generative AI solution available to all firm types in the FactSet Workstation. Transcript Assistant currently has approximately 4,000 active users.

Mar 6, 2024 | insight.factset.com | Lucy Tancredi |Ivo Kolarov |FactSet Insight

In this final installment of our six-part series on overcoming generative AI challenges, we share observations and perspective on the legal and ethical landscape of this evolving technology. Both the creators and users of Large Language Models can face legal and reputational consequences from LLM hallucinations. In one example, a model made up a false sexual harassment case against a real professor and cited a seemingly credible—but nonexistent—article from the Washington Post.

Mar 5, 2024 | insight.factset.com | Lucy Tancredi |FactSet Insight |Ivo Kolarov

Given investors’ question throughout last year of whether the US would achieve a soft landing, we used machine learning to analyze the risk on a historical basis. We also discuss the key insights from that time period and highlight 2024.