You Are Probably Experiencing these Forecasting Problems
Demand Forecast should be a forecast of future need from your customers. Most people fail to notice the little things wrong in their forecasting software that result in expensive over stocks and out of stocks. The 3 hot issues are: integer based forecast (whole number forecast), big data not being used in the forecasting math and demand planning software used for demand forecasting.
Forecast is a whole number, not a Decimal. What?!?
- Every Forecast Period is Wrong to some degree. Those ‘degrees’ of error result in too much safety stock and outs at the same time.
- A whole number forecast cannot be used effectively for slow and intermittent demand product. Worse, forecast systems that use time series or time series with regression analysis will never calculate slow and intermittent demand forecast correctly. The forecast errors require large costly human interventions, some call it job security. Also, the poor forecast creates costly overstocks and out of stocks.
Run the math for one example, a product need of 1 a month in a four-week month. Run your safety stock calculation using .25 for a weekly forecast for 4 weeks and select one week to have sales 1, the other weeks sales 0. Then calculate your safety stock using three weeks of forecast 0 and one week forecast 1 against same sales pattern. Now multiply that result across the thousands of products that have slow and intermittent demand.
Forecasting Software is Expensive to Fix, Don’t Expect a Fix
Does your wholesale or retail forecasting software use a whole number forecast? Research the beginnings of the software you use. You will probably find the software was built for manufacturing. Most people fail to realize that when a software program architecture considers forecast as a whole number, the forecast errors are expensive. When software is designed around a forecast as an integer(whole number) it is often financially impossible to convert the software and current customers to a decimal based forecast.
Integration of Forecast into Customer Other Data Creates a Larger Block to Software Updates
Hundreds of calculations and reports use that whole number forecast, to change to a decimal forecast is cost prohibitive. The lines of code through the software program that expect a whole number will inflate the cost of updating the code. Add to that complexity the fact everyone using that software creates reports and other data with the whole number forecast. Those reports and analysis tools need updates to use integer based forecast. The complexity and cost are huge, it is far cheaper to get marketing to write materials that turn attention away from the integer based forecast error costs.
Misses in Big Data, Your Forecasting Algorithms Don’t Know Type of Sales?
Does your forecast algorithm use sales data broken out by sales type? The common sales types are regular, lost, promo, and closeout. If your forecast system is only using total aggregate sales, then it’s a sales forecast model, not demand. To be a real demand forecast model the algorithms must be able to accept data on the entire sales picture, not one type of sale.?
Expensive Lost Sales issues in some Forecast Systems
- One month’s outs get added to next month’s demand. While this might have worked long ago, in the digital age, people alternate source. When you are out they get product from another place, customers don’t wait until next month.
- Lost Sales data is only a KPI – meaning the user must adjust the forecast manually after a reforecast to fix the lost sales issue. A KPI told you to fix something that a real demand forecast solution would have fixed already.
Demand Planning is not Demand Forecasting
Know Before You Buy any forecasting software the answers to these three questions. Is your forecast integer based, a whole number, no decimal? Many retail and wholesale companies bought forecasting software that was designed for manufacturing, yikes! Add the issue where type of sale is not considered in the forecast algorithm and the re-forecast can have a drastic impact on business. A sales forecast is generally higher than demand. Why, ever talk to a sales person who said I plan to sell less than last year? A sales forecast will be higher than demand most of the time. Demand Plans are designed around a store, floor space, and – the big point – unlimited inventory. Have you ever seen a plan that includes lost sales and close outs?
The Digital Age, the Internet of Things and Demand Forecasting
The digital age and the internet of things continually change the way people buy goods. It makes sense to review your forecast tools and find the right tool for your business. At Data Profits, we talk with a lot of people about Demand and how demand forecasting should correctly impact replenishment. Call us for ideas and or ask for a demo and see how our iKIS solution can improve your sales and inventory in less than 90 days when the other apps are still installing. Are you ready to ‘Tighten the Links in your Chain?’™
- Lead Time Forecasting - February 7, 2019
- Data Profits in Gartner’s 2017 Retail Replenishment and Forecasting Software Guide for the Sixth Year - February 13, 2018
- Data Profits Releases 4 Easy Replenishment Ideas that Adapt to the Digital Age - July 20, 2017