Forecast Accuracy Metrics

 

Most people know that one of the key components of the safety stock calculation is forecast error. It makes sense that if you knew exactly how much you were going to sell of each of the items you stock, you wouldn’t need safety stock, right? That precise knowledge of your upcoming demand would reduce how much you have to invest in your inventory and increase your profitability. On the other hand, you would stock the exact quantities that you were going to sell so you would also not have any out of stocks. So you wouldn’t lose any sales from not having product in stock, and your sales would go up.

Of course, in the real world, it is impossible to have 100% forecast accuracy. But is it possible to improve your forecast accuracy by 5%? How much financial impact would that have? How do you measure it? How much effort would that take?

Forecast Accuracy: The Opportunity for Profits

As for the financial impact of increasing forecast accuracy, there have been several studies to estimate what kind of impact an increase in forecast accuracy has on your profitability.

The Supply Chain Council studied 67 companies and found a definite correlation between higher forecast accuracy and higher fill rates:

Forecast Accuracy Correlated to Higher Fill Rates

Improved fill rates translates into fewer lost sales and fewer backorders, which results in increased revenues.

While improving fill rates, improved forecast accuracy lowers the inventory days requirement:

Inventory level vs forecast accuracy

So improved forecast accuracy improves fill rates and lowers inventory at the same time.

So how does this all translate into increased profitability? When analysts have studied companies that were best in class in demand forecasting, they found that these companies average*:
15% less inventory
17% higher perfect order fulfillment
35% shorter cash-to-cash cycle times
1/10th the stockouts of their peers

In addition, every 3% increase in forecast accuracy increased profit margin by 2%.

  • * Source:  AMR Research 2008

These improvements in inventory efficiencies then translate into improved financial metrics:
10% improvement in earnings per share (EPS)
5% increase in return on assets (ROA)
2.5% gain in profits

So indeed, an improvement in demand forecasting can have significant impacts on a business, driving all the way to the bottom line.

Forecast Accuracy: Measuring the Improvement

Unfortunately, most wholesalers, distributors and retailers do not track their forecast accuracy or forecast error.  In order to improve your forecast accuracy, you have to know where you are starting from.

The first thing we do for our clients is to start generating accurate forecasts for each SKU at each stocking location, and we also put the forecast accuracy metrics in place to monitor their accuracy and error going forward. For various reasons, the forecasts can get off track. Your business can have a couple of months of slow sales. Or on the other hand, you could have consecutive record months in sales. This could be an anomaly or it could be a trend. Either way, Thrive’s forecasts accuracy metrics will monitor the change in demand and alert the users and/or make adjustments to the forecast settings as necessary.

A few of the many Forecast Accuracy and Error Metrics that Thrive tracks:

– Forecast accuracy
– Forecast error
– Mean Absolute Percent Error (MAPE)
– Mean Average Deviation (MAD)
– MAD Percent

Forecast Accuracy: Improvement is Now Easier Than You Think

First off, why do companies struggle to improve their forecast accuracy?

The companies we work with (wholesalers, master distributors, and retailers) must manage thousands of items which further compounds the challenges of delivering perfect orders and managing forecast accuracy. An AMR Research study shows that the more items that need to be managed, the fewer perfect orders and increased forecast error.
Number of Items correlated with Perfect Orders - Forecast Error

Most wholesalers and retailers rely on their ERP system to plan their inventory.  As part of this process, most ERP systems calculate a ‘usage’ number rather than a true forecast, often using a moving average.  The accuracy of ERP ‘usage’ numbers is typically between 35% and 50%, or even lower for companies with seasonal demand and intermittent demand.

Thrive routinely generates statistical forecast accuracy at 90% to 95% for our clients so we often double the forecast accuracy lowering the forecast error, which creates significant efficiencies with safety stock holdings.

As a cloud based offering, Thrive’s demand forecasting system can be implemented within weeks leveraging the demand data from your ERP system. We provide a structured implementation delivered by people with strong domain expertise to make the process much easier than other enterprise software implementations while delivering a measurable impact on your inventory performance and profitability.

Forecast Accuracy: A Key Performance Indicator (KPI)

We are working hard to create a paradigm shift for wholesalers and retailers even beyond just measuring and monitoring the Forecast Accuracy of all SKU’s to considering the aggregate Forecast Accuracy number as a KPI with accountability and visibility at the senior management level.

Why is this so important?  Because the Forecast Accuracy KPI shows how well your company is predicting its upcoming demand. This effort to improving its prediction capabilities will improve overall planning, and make your business much more agile relative to market changes.  If you also measure the accuracy and error of your S&OP inputs to the statistical forecasts, you can gauge how well your salespeople can forecast upcoming business, especially with key accounts.

Possibly most importantly, the Forecast Accuracy KPI will alert you to gaps when inventory issues will arise.  If the forecast accuracy is dropping, you are about to start experiencing higher than normal stockouts, or possibly overstock.

Regardless of the specific forecast accuracy metric your company can achieve, the focus on it and ongoing effort to improve your company’s ability to better predict upcoming demand will significantly improve your business financially, improve your customer service, and transition the company from a reactive one to a proactive one.