Sales forecasting

 Sales forecasting refers to predicting future sales levels and sales trends.
 It is the process of predicting how much revenue a company will generate within a
specific timeframe in future. This could be a week, month, quarter, or even a year.
 The benefits of sales forecasting to a company include the following:

1. It assists in planning future production levels

 The questions how many products should be manufactured and how much raw
materials should be purchased need to be answered. This will allow for a more
efficient use of the firm’s resources, in particular labour which is normally a firm’s
highest cost. It will identify recruitment and training needs, or depressingly the
requirement for redundancies.

2. It helps a company in managing and planning its cash flow

 Being able to accurately predict future sales aids cash flow management as it helps to
calculate liquidity. Examining variations in sales and predicting future sales can help
the firm in drafting budgets and evaluate the need for additional sources of finance.
Lenders will be more likely to supply additional funds if they can see that the firm
will be able to repay on time.

3. Improvement in stock control

 Accurate sales forecasts will underpin stock ordering and ensure that production has
the raw materials when required. This knowledge of how much to produce will
contribute towards improving stock control

4. Helps in developing an effective marketing plans

 Forecasting is also beneficial for developing effective marketing plans. When

businesses can foresee a dip in sales, it's especially important to ramp up targeted
 marketing efforts. Business forecasting allows them to see where sales are lacking and
then tailor promotions to fill that gap.

5. Helps in preventing staffing issues

 Recognizing the importance of forecasting can help correct any staffing issues
companies may be experiencing. By assessing the rise and fall of demand each month,
day or hour, managers will have a better idea of which shifts will require the most
labour on hand and be able to plan ahead.

Sales forecasting techniques

Time series methods

 This method of sales forecasting is based entirely on past sales data.

 Sales records are kept over time and, when they are presented in date order, they are
referred to as a time series.
 It is useful when the market forces are somehow stable and the market shows least
erratic behaviour. Actions taken by the firm and the competitor’s move are not taken
into account.
 Historical data are used to project future events. For example, past sales are used to
project future sales. However, future events are often different from past events,
which make the accuracy of such methods far less than 100 per cent.
 It can be carried out using the following methods:

(a) Extrapolation

 The most basic method of predicting sales based on past results is termed
extrapolation. It means basing future predictions on past results.
 The recent past sales are given more weight than the earlier pasts. The objective is to
smooth out fluctuations in the time series for accurate estimation of sales forecast.
 When actual results are plotted on a time series graph, the line can be extended (or
extrapolated) into the future along the trend of the past data.
  This simple method assumes that sales patterns are stable and will remain so in the
future. It is ineffective when this condition does not hold true.
 An example of extrapolation is shown below

(b) Moving averages

 The method suggests drawing an average of the sales of a number of years to predict
the sales of a coming period. The objective is to smooth out the fluctuations and
provide a close estimate of the forecasted sales.
 The sales of previous years are given equal importance
 This method is more complex than simple graphical extrapolation. It allows the
identification of underlying factors that are expected to influence future sales. These
factors include:
 a) The trend – the underlying movement in a time series
b) Seasonal fluctuations – the regular and repeated variations that occur in sales data
within a period of 12 months. For example, climatic changes, festival periods,
Christmas occasions, etc., take place every year at a particular time period and these
influence sales for some products. The sales of garments, consumer durables pick up
during festival times.
c) Cyclical fluctuations – these variations in sales occur over periods of time of much
more than a year and are due to the business cycle. Cyclical variations represent the
ups and downs in the business and are better understood by studying the nature of the
business cycle. Ups in business cycle mean prosperity and downs mean recession.
d) Random fluctuations – these can occur at any time and will cause unusual and
unpredictable sales figures – examples include wars, natural calamities, poor weather
or negative public image following a high-profile product failure.

An example of a moving average is given below:

Advantages of moving averages

 It can be reasonably accurate for short-term forecasts in reasonably stable economic

conditions. This method produces a forecast that takes account of regular variations so
is more accurate than simply projecting a trend line.
 Helps in identifying seasonal patterns – Data points variances measured and
compared from year to year can reveal seasonal fluctuation patterns that can serve as
 the basis for future forecasts. This type of information is of particular importance to
markets whose products fluctuate seasonally, such as commodities and clothing retail
businesses. For retailers, for instance, time series data may reveal that consumer
demand for winter clothes spikes at a distinct time period each year, information that
would be important in forecasting production and delivery requirements.
 It assists in planning for future – through identifying the average seasonal variations
for each time period

Disadvantages of moving average

 Forecasts further into the future become less accurate as the projections made are
entirely based on past data. External environmental factors can change so that past
results become an unreliable indicator of the future.
 The moving average method does not take qualitative factors into account.
Forecasting for the longer term may require the use of more qualitative methods that
are less dependent on past results.

Other methods

a) Delphi Method

 It is the process of gathering a panel of experts and engaging in several rounds of

questions about how to make certain business decisions or solve an organizational
problem. Every answer the experts provide is anonymous. After each round,
facilitators review and sort through all the answers.
 The experts do not meet and they are anonymous to each other. After each round of
questionnaire results have been collected, they are summarised and sent back to all the
experts on the panel. In this way, the ‘extreme’ responses from the experts are oft en
amended and moderated so that, eventually, a consensus is reached that represents the
most likely ‘correct’ forecast.
 The main purpose of the Delphi method is to encourage these experts to settle on a
mutual agreement and to establish a group consensus.

Advantages of Delphi method

  A company gains knowledge from experts – The Delphi method is a great way to
settle any discussions or resolve complex problems the company and other team
members may have. Experts can all come to a logical agreement that could be
beneficial to the organization.
 Anonymity for unbiased responses – Delphi participants offer anonymous responses
during the group process. Being able to answer without fear of repercussion or
judgement from group opinion encourages honest responses.
 Time and cost-effective method of obtaining expert group opinion – Employing
the Delphi method using online tools avoids the cost of hiring, and transport to, a set
destination for the Delphi method to be implemented. Time consuming, lengthy
discussions are avoided due to the controlled feedback the Delphi method uses, and
the expert panel are not tied to a set time and date, increasing flexibility and
broadening the range of experts you have access to.

Disadvantages of Delphi method

 Limited open discussion –the Delphi technique uses controlled feedback, meaning
ideas are not openly discussed by participants (questionnaire responders) who may
not be able to elaborate in the same way as other research techniques. This restriction
however may mean that the Delphi method may not be as helpful where opinions are
highly polarised and deeper investigation may be required.
 Requires commitment if multiple rounds are required – The Delphi method can
sometimes require participants to be engaged and respond to more than one round of
questionnaires, which may include many similar questions to those already answered.
This can cause a practical problem if participants become disengaged or stop
responding, affecting the magnitude (and potentially the quality) of the results.
 Interpretation of study results are highly dependent on responder expertise –
The Delphi method is often used where there is no absolute answer to a question
existing and opinion is the most valuable data asset available. This places strong
importance on the qualification of the responder group in order to answer the survey
questions in hand. Unless there is confidence in the level of experience and expertise
of the responder group then it will be challenging to reach clear conclusions or
recommendations.
b) Jury of experts

 The jury of experts uses senior managers within the business, who meet and develop
forecasts based on their knowledge of their specific areas of responsibility. This is
quicker and cheaper than the Delphi method, but it lacks the external view of market
conditions and consumer trends that the Delphi method offers. It is sometimes
referred to as the jury of executive opinion.

c) Consumer surveys

 These are a form of market research and the questions may either be quantitative in
nature (e.g. asking for likely future levels of demand) or qualitative (e.g. asking for
reasons behind future demand choices). For greater accuracy, the sample of
consumers selected must be large enough to be as fully representative of the total
number of consumers for a product as possible.

Problems of sales forecasting

 Customer buying behaviour may change – for example, customers may suddenly
decide that the product is unsafe or unfashionable following a problems, such as a
fault emerging with the product, or ethical issues regarding the way the product was
made.
 The original market research was poor – this may be because the sample was too
small or was unrepresentative. Also, it may be because the results were wrongly
interpreted (because the firm was rushing to launch a product.
 The experts were wrong – even the best informed people may misread a situation
and make mistakes. This may be due to use of conflicting forecasts of growth in the
economy that are published in the media.

The reliability of sales forecasts

The reliability of sales forecasts is depended on the following:

 The trend has been extrapolated and the market conditions have continued as before
 A test market is used and is truly representative of the target population
 The forecasts is made by experts and have good insight into the market and future
trends
 The firm is forecasting for the near future – it is usually easier to estimate what sales
will be next week rather than estimating sales in five years