Big Decisions Blog

The latest news and insights from the team at Hubbard Decision Research
Using LLMs to Generate Models in Excel

Using LLMs to Generate Models in Excel

Background  As a senior quantitative analyst at Hubbard Decision Research, I spend a significant portion of my day creating Monte Carlo simulations to analyze complex investment problems. The process involves decomposing the problem into relevant variables,...

read more
Optimizing IT Infrastructure for Enhanced Banking Performance

Optimizing IT Infrastructure for Enhanced Banking Performance

Client: A Leading Silicon Valley-Based Financial Institution Industry: Banking Objective: To conduct a cost-benefit analysis for consolidating data center operations, which involves advanced Monte Carlo models and data-driven dashboards Executive Summary A top-tier...

read more
Optimizing Prices for Project Bids

Optimizing Prices for Project Bids

Summary: By measuring how their experts price projects and price elasticity, HDR was able to build our client a pricing model that tripled their operating income. A few years ago, a medium-sized manufacturing firm came to HDR to help redefine how they quote projects....

read more
Calibrating Chat GPT for Its Overconfidence

Calibrating Chat GPT for Its Overconfidence

In a previous article, we measured how calibrated Chat GPT 4 was at providing a 90% confidence interval. During the experiment, after explaining what is meant by a 90% confidence interval, Chat GPT would provide a stated 90% interval that would only contain the actual...

read more
Is ChatGPT as Overconfident as Humans?

Is ChatGPT as Overconfident as Humans?

"It's not what we don’t know that hurts, it’s what we know for sure that just ain't so." The quote above is often attributed to Mark Twain. Ironically, the authorship of this quote being somewhat uncertain, beautifully illustrates the very point it makes....

read more

Newsletter