Sales Forecasting (Cambridge International A-Level Business)

The need to forecast sales

• Sales forecasts predict future revenues *based on past sales figures

  • They are an important business planning tool
  • They can be used to identify trends in sales which can then be compared with the market as a whole

• They commonly focus on what will happen in the future to:

  • The volume and value of sales
  • The size of the market
  • Sales as a result of promotional activity
  • Sales as a result of cyclical factors

• Sales forecasts are an important tool to support planning and improve the validity of cash flow forecasts

• Businesses use sales forecasts to determine resource requirements, such as

  • How many staff are needed
  • How much stock is required
  • Whether capacity *needs to be expanded or reduced
  • Whether equipment needs to be upgraded or replaced
  • How much and which type of finance is required
  • Whether and when promotional activity (e.g. advertising) is required

Time series analysis

• Raw sales data on its own may not be very useful for sales forecasting

  • It can be hard to spot patterns, trends or seasonal changes by looking at rows of data or, even, data in a graph, especially if sales are volatile

    • In the example below, it would be difficult to draw a line of best fit in order to extrapolate and make sales forecasts

Example of raw data plotted in a chart

Sometimes it is difficult to identify a line of best fit to extrapolate a trend as raw sales data is volatile

• Businesses may uses time series analysis to smooth data, making it easier to predict likely sales in the future based on past performance

How to conduct a time series analysis

Step 1: Calculate moving totals

• In this case, a three-month moving average will be calculated

• Add together sales for January, February and March

• Place the total alongside March

$=15,425+9,647+12,379\,\,=37,451$

• Now do the same for February, March and April
• Place the total alongside March

$=9,647+12,379+17,002\,\,=39,028$

• Now do the same for March, April and May
• Place the total alongside May

equation$=12,379+17,002+10,204\,\,=39.585$

• Repeat the process for each subsequent group of three months

Completed table: 3-month moving totals

The three month moving total is a sum of each three months of sales data

Step 2: Calculate moving averages

• Divide March's moving total by 3
• Place the average alongside February

$=37,451\div3\,\,=12,484$

• Divide April's moving total by 3
• Place the average alongside March

$=39,028\div3\,\,=13,009$

• Divide May's moving total by 3
• Place the average alongside April

$=39,585\div3\,\,=13,195$

• Repeat the process for each subsequent group of three months

Completed table: 3-month moving averages

The moving average smooths data that can be plotted in a graph to allow a line of best fit to be applied

Step 3: Plot the moving averages and identify the line of best fit

• Include as many data points above the line as below the line.

  • Watch out for outlying data - if there is more than one outlier above the line, adjust your line of best fit upwards
  • Similarly, if there is more than one outlier below the line, adjust your line of best fit downwards

The line of best fit

With smoothed data, a line of best fit can be identified

Step 4: Extrapolate to forecast future sales

• Extend the line of best fit to predict future sales values

Extension of the line of best fit

Sales of 17,750 in June can now be forecast by extending the line of best fit

• In this cases, the line of best fit is extended to June, allowing a prediction of 17,750 sales in that month

Qualitative sales forecasting

• Qualitative sales forecasting involves predicting future sales based on non-numerical data

  • This may include expert opinions, market experience or customer feedback, rather than historical figures or statistical analysis

• Qualitative forecasting relies on judgement, knowledge and experience rather than data modelling

• Methods include

  • Expert opinion

    • Insights from experienced managers, industry specialists or consultants

  • Sales force estimates

    • Forecasts made by sales staff based on their direct interaction with customers

  • Customer surveys

    • Using feedback from potential buyers to estimate future demand

• It is especially useful when a business

  • is launching a new product with no past sales data
  • is entering a new market or responding to major market changes
  • wants to understand consumer attitudes and future buying behaviour

Advantages of qualitative sales forecasting

• Useful when historical data is unavailable

  • This makes it ideal for use with new products or markets

• Incorporates expert judgement

  • Makes use of real-world knowledge and insights that numbers can’t always capture

• Flexible and adaptable

  • Can be quickly adjusted based on changing market conditions

• Encourages team involvement

  • Sales teams and managers contribute ideas, improving internal communication and morale

Disadvantages of qualitative sales forecasting:

• Subjective and prone to bias

  • Forecasts may reflect opinions rather than facts

• Less accurate than quantitative methods

  • Without numerical data, predictions may be vague or inconsistent

• Hard to measure reliability

  • It is difficult to test or prove whether a forecast is correct until actual sales occur

• Time-consuming

  • Gathering expert opinions or conducting surveys takes time and requires coordination

The impact of sales forecasting on business decisions

• Accurate sales forecasting can help a business plan ahead and make informed decisions across functional areas
• However, sales factors should be considered alongside other research on likely future business performance

Sales forecasting and functional decision making