Happiness comes from exceeding expectations.

Happiness causes your stock price to go up.

Happy investors are a good thing.

Time Series Forecasting Part 1 of 10 KDD Analytics

This also works in reverse (which is a bad thing). Expectations come from past performance, market analysts and company guidance. IROs don't control the first two but they can provide guidance.

Predicting the future is an exercise in probability rather than certainty. Businesses engage in various levels of sophistication in trying to bound the likelihood of future states to support their business plans.

Guidance is not an SEC requirement, so IR is confronted with a range of options in providing guidance to the market. While we're not going to address the pros and cons in this post, best practices are clearly in favor of providing investors the information they need the company's plans and expected performance, in the short and long term. The better the quality of the information you provide, the more it will help analysts and investors understand your company, driving interest, volume and coverage. Investors reward transparency, but the value of that transparency is built on trust in the quality of the information.

If a company tries to game the system and manipulate investor expectations, it will lose trust, and investors.

An IRO doesn't prepare the company's forecasts, but does represent the investor's interests in the process. To build trust, the IRO can require a transparent and systematic set of internal processes and methodologies for preparing guidance and then be clear and consistent in providing that information to the market.

Time series methodology is a moderately sophisticated yet cost effective way to generate forecasts. It is a statistical approach which bases forecasts on the past behavior of the data series in question (e.g. monthly sales).

Since forecasting techniques may be outside of the experience of most IROs, we've asked our CAO and Economist Kevin Duffy-Deno to produce a series of posts on the techniques for non-experts.

Rather than a treatise on forecasting, this series will present a practical methodology and some of the lessons learned performing time series forecasting for clients. Equally important, as with all forecasting methodologies, there are pitfalls you should know about. The IRO's credibility is the company's credibility.

Kevin announced the first of the ten part series, Practical Time Series Forecasting – Introduction on December 4th so please check it out and follow his blog. We will mark each issue here and include to those on our emailing list.

“The only thing I cannot predict is the future.”
- Amit Trivedi, Riding The Roller Coaster: Lessons from financial market cycles we repeatedly forget

Maybe you can't predict the future, but if you're going to provide guidance, do it right, do it consistently and the market will reward you.

Topics: business intelligence, investing, analytics, forecasting, research, finance

Tom Marsh

Written by Tom Marsh

Tom has served as CEO of Bintel since cofounding the company in 2019. Before that he was COO of ai-one inc. where led the projects for NASA Marshall, SwissRe, Boeing and FedEx. For the past 15 years he has specialized in artificial intelligence applications for enterprise and government with a critical integration of Subject Matter Experts, AI, data, and visualizations. For FedEx this included topic classification and visualization of customer experience data collected weekly from survey data on FedEx.com. A project with an Army military intelligence group involved the development of a sophisticated intelligence platform that included GEOINT and provided situational awareness for an allied military. His current mission is to bring that caliber of solutions to counties in the West.