3.3.1 Quantitative Sales Forecasting

Moving Averages

• When looking at sales figures from previous years, we can take an average of a cluster of years at a time.
• If we look at lots of clusters, we get a much better view of sales trends.
• This can also be done for months or quarters.

3-Point Moving Average

• The first three points are added together and then divided by three to give an average.
• Then again for the second, third and fourth points.
• Then again for the third, fourth and fifth points.

$$(31 + 28 + 15) / 3 = 24.67$$ $$(28 + 15 + 45) / 3 = 29.33$$ $$(15 + 45 + 40) / 3 = 33.33$$ $$(45 + 40 + 41) / 3 = 42$$

4-Point Moving Average

• Better for businesses that experience seasonal trends and work in quarters. | Year | 2006 | 2007 | 2008 | 2009 | 2010 | 2011 | 2012 | 2013 | 2014 | 2015 | |---|---|---|---|---|---|---|---|---|---|---| | Sales | 125 | 130 | 130 | 150 | 140 | 155 | 180 | 190 | 210 | 230 | | | | | | | | | | | | |

$$2006-2009 = 535$$ $$2007-2010 = 550$$ $$535 + 550 = 1085 (8 point moving total)$$ $$1085/8 = 135.63 (2 dp)$$

Extrapolating the Data

🔗 Extrapolating – Predicting future figures based on what has happened before. Often done by extending the trend line.

• The simplest way to predict the future is to assume it will be similar to the past.
• Extrapolation is predicting future figures based on what has happened before.
• This can often be done by extending the trend line on a graph by eye.

Pros and Cons of Using Moving Averages and Extrapolation

• A simple method of forecasting
• Quick and cheap (not much data required)
• Unreliable if there are significant fluctuations
• Assumes past trends will continue
• Ignores qualitative factors (E.G Changes in taste and fashion)