Forecasting Process for Demand Planning

The first step in developing a forecasting process is necessarily to consider the main reasons for producing a forecast.  Every company is different, but some of the reasons for needing an accurate demand forecast are likely to relate to S&OP, production planning, inventory management, sales planning, warehouse capacity, workforce and financial planning. 

Early decisions are needed on some key components in the demand forecasting process including the historical data to be used, time periods, time horizons and level(s) of detail for products / customers.  Forecasting methods may include time series forecasting, causal modelling and, of course, commercial judgement.

Some of the key components in a demand forecasting process are:

• Forecast accuracy measurement and reporting

• Review of forecasts needing attention

• Historical data cleansing for promotions and other outliers

• Dealing in the best possible way with seasonality

• Creation of an unconstrained demand forecast using chosen methods

• Addition of market intelligence / promotional planning

• Application of commercial judgement

• Reconciliation of alternative opinions / versions of the forecast

Forecast Solutions can help with all aspects in the development of a successful forecasting process.

Email:  enquiry@forecastsolutions.co.uk

Time Period and Time Horizons

The majority of businesses use months or weeks as the basis for forecasting.  If monthly data is adequate this has the benefit of simplicity and relative ease in the calculation of seasonal indices.  If accounting months of the type 5wk, 4wk, 4 wk are used there is usually the need to adjust the historical data before forecasting to take account of unequal period lengths, then to reinstate the period weightings into the final forecast.

Weekly forecasting may be needed when there is an active promotions programme, or if reconciliation with weekly customer forecasts is needed.  The expectation that a weekly forecast will be more accurate than monthly, however, is sometimes not realised due to the greater volatility in weekly data and, particularly, due to complications in seasonal analysis.

There may be a need for daily forecasting, for example for products with a very short shelf life or for the forecasting of daily activity at call centres. With daily forecasting there is a need to cope with profiles of day within week as well as weekly seasonality and there are a number of different approaches that can be used in this somewhat difficult task.

 Statistical Forecasting Methods

Statistical forecasting methods are usually valuable when a consistent demand history of two years or more is available.  The most commonly used family of methods is referred to as time series forecasting.  Here, the historical data is analysed to identify the seasonal pattern and trend that applies to the entity being forecast and these characteristics are extrapolated forward to create a forecast.  Time series forecasting does make the assumption ,however, that the overall environment will stay constant. 

Another family of statistical forecasting methods is called causal modelling, where analysis is conducted of the company's demand history together with historical data on one or more suspected causal factors such as weather, price or economic indicators.  Statistically valid relationships between demand for products or services and one or more causal factors may be found. These may alone be the basis for a forecasting solution or can sometimes be combined with a time series forecasting method.

Forecasting Software

If the forecasting process that is required includes statistical forecasting, there should be consideration of the software that is needed to support it.  It may be possible to construct forecasting routines in Excel to fulfil this, but the need for specialist software increases in the case of businesses that offer large numbers of products and where there may be a benefit in forecasting at more than one level of detail.  Specialist software may incorporate a good choice of statistical forecasting, support multi-level forecasting and have built in forecast archiving facilities to support forecast accuracy measurement and reporting.

Complexity in the forecasting process, however, does not necessarily mean that specialist software is the best way to go.  The complexity may lead to a software requirements specification leading to a choice of very complicated and unaffordable software.  In some ways Excel is good because it can be tailored to the business's exact requirements, but Excel may be difficult to manage with a very large number of products.

 Application of Commercial Judgement

 Whether or not statistical forecasting methods are used for forecasting it is always valid to check the forecast with commercial judgement.  If  adjustments are made, it is good to have clarity as to which individuals or groups have access to suggest or make changes and ideally the changes should be documented.  With forecast amendments the emphasis should be on important and significant differences, rather than trying to review everything.

 Forecast Reconciliation

Sometimes there may be different points of view on certain aspects of the forecast, or sometimes there may be a complete different version of the forecast.  Such forecasts may have been produced by a sales team or possibly by a major customer.  A reconciliation process may be needed, whether it be based on a mathematical approach or through a regular meeting of individuals.  If there is a S&OP process in place the reconciliation may well be covered as part of that.

Forecast Accuracy Measurement

A major part of any demand forecasting process is the achievement of the best possible levels of accuracy, therefore forecast accuracy should be measured at the start of every forecasting cycle.  All businesses are different in terms of the levels forecast accuracy that are possible and targets should be challenging, but achievable.