This page demonstrates how Hedieh and I have used AI to improve financial modelling in a realistic and helpful manner. She has demonstrated how to use Claude to answer a modelling test from a case and she has done a similar thing with an information memorandum. She has created a set of skills to nicely format a model. She has also used AI to verify a model and do some auditing of a model. I have heard how AI can create three statement models (as you may know three statement models make me vomit because creating financial statements is really no big deal). I cannot imagine letting AI make models without knowing how to make the models yourself. The fundamental reason excel was used in the first place in financial modelling is that unlike code such as python or C++, people can follow the input data, all of the equations and easily make changes to outputs and presentation. Doing things like creating timelines, setting-up and InputC page, working through operating cash flows should go really fast. Alternatively you can use a template model and just fill in the data. The work Hedieh has done is very intersting, but I am not sure how much it will really change things.
For a few years I have been having discussions with a modelling company that makes large project finance models. The big issue was at the end of the model the time it takes for running the copy and paste routine in a model and also a goal seek function. The time it takes to run a model is surprising as processing of calculations on a model is so fast with any computer and the calculations for even a large project financial model are very small compared to gaming applications and other scientific applications. Many years ago I found that if I could: (1) take the data inputs from the excel financal model; (2) put the data into a programming application (python, C++, html, or VBA), (3) re-do the modelling equations in the programming language; and (4) put the results back in excel, the problem with the timing of the model could be solved. I was able to demonstrate this with large models that had very complicated financing during construction formulas (nuclear plants), with very complicated tax equations that had constraints on the interest charged for shareholder debt and tricky timing issues, and with many different debt issues including equity bridge loans and standby facilities. It was time consuming to replicate the equations but the result in terms of processing time was dramatic. I have put a couple of examples of the time saving below. These include:
- A large model that had complex tax equations, multiple debt issues, tricky timing issues with political risk and goal seek formulas.
- A large model with reconciliation to actual data in the construction period and different generating units.
- A model that consolidates projects into a fund and becomes large with circular references
- A model that has general InputC and InputS and fully replicates goal seek formulas using a method called bi-sectional calculation techniques.
.
With that long introduction, the objective and the challenge are clear. To implement the process Hedieh and I have developed a few alternatives
- Making the process of easy to implement