UNIT 3

Sales Forecasting :Introduction, Simple Linear Regression & Multiple Regression model to
forecast sales, Forecasting in Presence of Special Events, Modeling trend and seasonality;
Ratio to moving average forecasting method, Using S curves to Forecast Sales of a New
Product

What is sales forecasting?

Sales forecasting is the process of estimating a company’s sales revenue for a specific time
period – commonly a month, quarter, or year. A sales forecast is prediction of how much a
company will sell in the future.
Producing an accurate sales forecast is vital to business success. Hiring, payroll, compensation,
inventory management, and marketing all depend on it. Public companies can quickly lose
credibility if they miss a forecast.

Forecasting goes hand-in-hand with sales pipeline management. Getting an accurate picture of
qualification, engagement, and velocity for each deal helps sales reps and managers provide data
for a reliable sales forecast.

A forecast is different than sales targets, which are the sales an enterprise hopes to achieve. A
sales forecast uses a variety of data points to provide an accurate prediction of future sales
performance.

Why is sales forecasting important for business?

Sales forecasting isn’t just about predicting numbers; it’s foundational to any business
strategy. Here’s why:

 Strategic decision making: Sales forecasts provide a clear picture of where a business is
headed, which factors into making decisions about product launches, market expansions, or
even potential mergers and acquisitions. Understanding these forward looking projections
can help businesses make informed decisions that align with their long-term goals.
 Resource allocation: A close-to-accurate sales forecast ensures that resources – whether it’s
labor, capital, or technology – are allocated efficiently. Proper allocation prevents over-
spending in areas that might not yield returns, and ensures that high-potential areas receive
attention and investment.
 Budgeting and goal setting: Accurate and reliable sales forecast data is foundational to
estimating future revenue and costs, as well as setting realistic yet challenging goals for
revenue teams. Such data-driven insights help businesses allocate resources efficiently,
ensuring that teams are equipped to meet their targets while also safeguarding a company’s
financial health.
 Proactive problem solving: One of the most significant roles for sales forecasting is the
ability to spot potential issues before they become major problems. For example, if a sales
team is trending below its quota, sales managers can take timely action, preventing minor
setbacks from escalating into significant ones.

What is regression analysis?

In statistics, regression analysis is a mathematical method used to understand the relationship

between a dependent variable and an independent variable. Results of this analysis demonstrate
the strength of the relationship between the two variables and if the dependent variable is
significantly impacted by the independent variable.

What is regression analysis in sales?

In simple terms, sales regression analysis is used to understand how certain factors in your sales
process affect sales performance and predict how sales would change over time if you continued
the same strategy or pivoted to different methods.

Independent and dependent variables are still at play here, but the dependent variable is always
the same: sales performance. Whether it’s total revenue or number of deals closed, your
dependent variable will always be sales performance. The independent variable is the factor you
are examining that will change sales performance, like the number of salespeople you have or
how much money is spent on advertising.

How To Use Regression Analysis To Forecast Sales

Let’s say that you want to run a sales forecast to understand if having your salespeople make
more sales calls will mean that they close more deals. To conduct this forecast, you need
historical data that depicts the number of sales calls made over a certain period. So,
mathematically, the number of sales calls is the independent variable, or X value, and the
dependent variable is the number of deals closed per month, or Y value.

Modeling Trend
Trend forecasting is a complicated but useful way to look at past sales or market growth,
determine possible trends from that da and use the information to extrapolate what could happen
in t future. Marketing experts typically use trend forecasting to he determine potential future
sales growth. Many areas of a business can use forecasting, and examining the concept as it
relates to sal can help you gain an understanding of this strategy.

Time Series and Trends :

Trend forecasting is quantitative forecasting, meaning its forecasting is based on tangible,

concrete numbers from the past. It uses time series data, which is data when the numerical value
is known over different points in time. Typically this numerical data is plotted on a graph, with
the horizontal x-ax being used to plot time, such as the year, and the y-data being use to plot the
information you are trying to predict, such as sale amounts or number of people. There are
several different types o patterns that tend to appear on a time-series graph.

Constant Patterns in Data :

When looking at sales numbers for example, a constant trend is seen when there is no net
increase or decrease in sales over time. The sales may increase or decrease at specific dates, but
the overall average stays the same. However, even if the average results are the same within a
year, there still can be seasonal changes. For example, sales levels may be consistently greater in
the summer and lower in the winter, although the average is the same in the entire year.

Linear Patterns in Data :

A linear pattern is a steady decrease or increase in numbers over time. On a graph, this appears
as a straight line angled diagonally up or down.

Understanding Exponential Patterns :

An exponential pattern is simpler than it may sound. Rather than a slow, steady increase over
time, an exponential pattern indicates slow, steady rising at an increasing rate over time. Instead
of a straight pointing diagonally up, this type of graph shows a curved line where the last point in
later years is higher than the first year, if the rate is increasing. An exponential trend for sales
might indicate that sales were very slow in early years, but the product has grown increasingly
popular each year as more people become interested in purchasing it.

More Complicated Patterns:

Trend forecasting can also deal with patterns that are much more complicated than constant,
linear and exponential graphs. For example, a damped trend ma may show there was an overall
increase in sales. for a number of years and then a sudden stop. A polynomial trend might show a
gradual increase, then stagnation in sales over time followed by a decrease in sales.

Forecasting Using Patterns:

Looking at data over a number of years and finding patterns, you can use this information to
predict future patterns. A trend means the same series of events is happening over and over. For
example, if there is a trend of constant sales each year with a decrease of sales in winter that is
offset by an increase in the summer, a person might use this pattern to predict that sales will
continue to be low in the winter. Put into action, a store manager might offer additional products
in the winter to help hedge against the expected drop in sales. However, forecasting isn't done
quickly by just looking at a graph. Forecasters may translate the a graph's patterns into a formula
to accurately predict what will happen in the future. They often use spreadsheet software that in
trend forecasting tools. comes with built in trend forecasting tools.

Seasonality
Seasonality is a characteristic of a time series in which the data experiences regular and
predictable changes that occur every calendar year. Any predictable fluctuation or pattern that
recurs or repeats over a one year period is said to be seasonal.

Seasonality in forecasting requires business owners and supply chain managers to identify which
goods have seasonal patterns and which do not. And for the goods that do fluctuate in popularity,
the challenge is in determining when they will see the highest and lowest demand.

The Importance of Seasonality in Forecasting

Understanding seasonal variation in forecasting is crucial to solving a two-fold business

problem. On the one hand, when you don't have sufficient product inventory or enough
employees to meet surges in consumer demand, you risk damaging the business' reputation and
relationships with customers.

On the other hand, an excess in inventory and too many staff members working during slower
periods result in inefficient use of labor and funds. Either way, the company can lose revenue
and miss out on profitable opportunities as a result.

There are three types of time-based seasonal patterns.

1. Weekly seasonality - This usually applies to general product consumption on particular

days of the week. For example, a gallup poll found that Americans on average spent the
most money on Saturdays and least on Mondays. This is likely the result of weekdays
leaving little time for shopping and entertainment as a result of work or school.
2. Monthly seasonality - This covers cyclical demand for goods and services over the
course of a month. For example, you may find that your customers spend more when
their paychecks arrive either at the beginning or the end of the month.
3. Yearly seasonality - This seasonality sees a predictable and recurring demand for goods
and services on an annual basis. As mentioned earlier, online retail sales surge during the
fourth quarter of the year due to the holiday season. Likewise, the back to school' period
also sees a consistent spike in demand for books and school supplies each year.

How to Manage Seasonal Demand

Considering the following practices could help improve the accuracy of your seasonal
forecasting model-

 Determine which products are seasonal - To detect seasonality, find a recurring pattern
in the demand of your products over time. Observe existing historical data within a
specific time frame and ask yourself this question, Can you see a similar demand pattern
year-over-year, month-over-month, or week-over-week? Next, find the correlation
between each year, month, or week. If you see a pattern, you have a reliable seasonal
demand.

 Know why and when spikes in demand happen - Next, understand the correlation
between spikes in demand relative to specific periods of time. Is it due to the weather? A
holiday, perhaps? Is it caused by man-made or natural factors? Understanding how these
variables influence your customers' buying habits will go a long way towards maximizing
peaks in demand and accurately estimating seasonality.

 Measure the size of these spikes relative to baseline demand - Once you know why
and when popularity for certain goods fluctuate, you then need to measure seasonal peaks
in demand and compare it with average (i.e., baseline) demand levels. Knowing this will
help prepare both the inventory and labor needs accordingly.

 Determine the reliability of your forecasts - The dynamic nature of the marketplace
means that forecasting seasonal demand cannot always be 100% accurate. However,
there are ways to improve the accuracy of your forecasts, such as by identifying demand
outliers and understanding their effect on your calculations. This will help in determining
the underlying causes and levels of error in previous forecasts and help in creating
seasonally adjusted data. For products or companies who have been operating for several
years, also consider going back as many years as you can to have as much historical data
to work with as possible. For newer products or product lines, it may be necessary to
cross-reference them with the syndicated market data of similar products.

Ratio to moving average forecasting method

The ratio-to-moving-average (RMA) forecasting method is a simple and widely used technique
for predicting future values of a time series. It involves dividing the actual value of a variable by
its moving average over a specified period of time, and using this ratio as a forecast for the next
period.

The ratio-to-moving-average (RMA) forecasting method is used to predict future values of a

time series based on its historical data. The RMA method assumes that the ratio of the current
value of a variable to its moving average will remain constant over time and uses this assumption
to make predictions about future values of the variable. The RMA method is a simple and widely
used technique for detecting trends and cyclical patterns in a time series.

The RMA method assumes that the ratio of the current value to its moving average will remain
constant over time, and uses this assumption to make predictions about future values of the
variable. This method can be useful for detecting trends and cyclical patterns in a time series.

The steps involved in the RMA forecasting method are as follows:

 Calculate the moving average for a specified period of time (e.g., 3 months).

 Calculate the ratio of the current value to the moving average.

 Use this ratio as a forecast for the next period.

For example, if the moving average for the past 3 months is 100, and the current value is 120, the
ratio would be 1.2. This would be used as a forecast for the next period.

The RMA method is a relatively simple and intuitive technique, but it may not be appropriate for
all time series data. It works best when there is a consistent and stable relationship between the
current value and its moving average over time. If the relationship is unstable or changes over
time, other forecasting methods may be more appropriate.

The formula for calculating the ratio-to-moving-average (RMA) method is:

RMA = (Current Value) / (Moving Average)

Where:

“Current Value” is the most recent value of the time series.

“Moving Average” is the average of a specified number of past values of the time series.

For example, if you want to calculate the RMA for a 3-month moving average of sales data, and
the current sales value for the current month is $50,000, and the average sales for the past three
months is $40,000, then the RMA would be:

RMA = $50,000 / $40,000

RMA = 1.25

This means that the current sales value is 1.25 times greater than the moving average for the past
three months. You can use this RMA value as a forecast for the next period.

Using ‘S ’curves to forecast sales of a new product

What is S curve ?

S curve is one of the most important concept when it comes to the Product Life Cycle (PLC) or
the Product Evolutionary Cycle (PEC). It is a widely used concept in marketing. It is called the S
curve because it looks like the letter S.

S curve is applicable to any business or startup where things move very slowly at first, then it
gains momentum and continues to grow and finally a stage where productivity or sales declines
and the market becomes saturated. S Curve equation enables one to know how large the sales
will become and whether the sales have touched the inflection point.

The S curve can be divided into 3 parts:

 In the initial stage, the sales generated are less due to many factors like low demand, high
competition in the market, poor promotion, and high costs associated with marketing.

 Then the sales start to increase with an increasing rate up to a point( known as inflection
point). This is due to greater public awareness and reduced costs due to economies of
scale.

 After the point of inflection, the growth rate of sales slows down. It means that only
existing customers continue to buy and the product has reached its saturation point.

Once any product reaches its saturation point in its product life cycle, it can either die at this
phase or if infused with new innovation and greater efficiency, it might create a newer S curve
from this phase.

S curves are used to plan, control, analyze, and forecast the progress and performance of a
product/project over a period of time. They are also used for cash flow forecasts, quantity output
comparison, etc.