CHAPTER 7:

FINANCIAL
FORECASTING
INTRODUCTION

Forecasting is looking at future sales, revenues, earnings,

costs, and other potential factors that are needed in the
operations of the firm. The main purpose of forecasting is to
lessen the risk of uncertainty that the firm will encounter in
creating a decision. In establishing a firm, determining first
the sales forecast. Different requirements are needed to
forecast the financial status of the firm. These are the needed
plan to conduct forecasting activities such as production plan,
inventory plan, and factory overhead plan.
RECIPIENTS OF FORECAST

1. Top People in the organization

They use this is a tool for setting long- range strategic objectives and
making capital budgeting decisions.
2. Production Manager
They use this as a tool to access the number of row materials that will be
needed in the production, the budget, schedule of production activities,
inventory levels, labor hours, and the schedule of shipments.
3. Purchasing manager
They use this as a tool to ascertain the volume or bulk of materials that
should be purchased for a particular period. This avoids overstocking or
understocking of inventories.
4. Marketing manager
they use this a tool to estimate how much sales should be made in a particular
period, and to plan promotional and advertising activities for the products.
5. Finance manager
They use this a tool to anticipate the funding needed by the firm and to
establish the firm’s cash inflows and outflows.
6. Human resource manager
They use this a tool to utilize the forecast to supply the human resource
needed in achieving the firm’s objectives.
7. School administrator
They use this as a tool to identify possible enrollees in a school year. The
figures on hand help determine the revenues to be obtained from the tuition
fees, the faculty to be hired, the planning of room assignments, and the
building of facilities.
FORECASTING APPROAHES
• QUALITATIVE(or judgmental) forecasts. This will cover the
following factors, intuition, emotion, personal experiences, and value
system. It is useful in formulating short-term forecasts and supplements
the projections made using any of the qualitative methods.

The qualitative forecasting methods are as follows;

1. EXPERT OPINIONS
2. DELPHI METHOD
3. SALESFORCE POLLING
4. CONSUMER MARKET SURVEYS
5. PERT- DERIVED FORECASTS
 QUANTITATIVE FORECAST Adopt different mathematical
models that rely on historical data and/ or casual variables

Two types of Quantitative forecasting are;

1. Time Series Forecasting
 Naïve Model
Moving average
Weighted moving average
Exponential smoothing
Trend projections
2. Associate or Casual models
3. Regression analysis
TIME SERIES FORECASTING
• It assumes that the future is a function of the past. The historical data are
used to predict the future using sequences with equal periods. The
sequence may be daily, weekly, monthly, quarterly, annually, or any equal
periods the firm think of.

DECOMPOSITION OF A TIME SERIES FORECAST

• Analyzing a time series means dividing the past data into components
and then projecting them forward. A time-series typically has four
components; Trends, Seasonality, Cycle, and Random Variations.

1. Trend is the gradual upwards or downward movement of the data over

time. Changes in income, population, age distribution, or cultural vies
may account for movement in trends.
2. Seasonality is a data pattern that repeats itself after a period of days,
weeks, months, or quarters.

There are six common seasonality patterns:

Period of Pattern “Season” length Number of “ Season” in pattern
Week Day 7
Month Week 4-4½
Month Day 28 - 31
Year Quarter 4
Year Month 12
Year Week 52
3. Cycle is a pattern of the data that happens every several years. It is usually done with
the business cycle especially in business analysis and planning.
4. Random variation are “blips” in the data caused by chance and not ordinary
situations. They follow no discernible pattern, so they cannot be assumed.

NAÏVE MODEL
- The simplest way to forecast is to assume that the demand in the next period will
be similar or the same to the demand in the most current period. It is considered as the
benchmark model.

The common advantages of using the naïve model are as follows:

It is not expensive to use.
It does not require any software or gadget even the use of technology.
Storing of data is based on the previous records.
It does not require or use complex mathematical applications.

In common disadvantage are as follows:

It does not explain casual relationships with the forecasted variable.
A sudden change in the variable for forecasting is not captured.

MOVING AVERAGE
-Here the number of period n, in which a series of averages will be created and
computed. It should be decided by the manager- in – charge. It should determine the
most appropriate number of periods that would result in the smallest forecasting
error.

The common advantages of the moving average are:

It is easy to use.
It is easy to understand.

The common disadvantage of the moving average is as follows:

It requires a lot of records and data.
It is difficult to update the records and data needed to facilitate a forecast.

The following formula is used in finding the moving average of order n,

MA(n) for a period t+1,
Where:
n= the number of observations used in the calculation.
The forecast for period t+1 is the forecast for all future periods. However,
this forecast is revised when new data becomes available.
WEIGHTED MOVING AVERAGE
-A weighted moving average (WMA) is more powerful and economical
compared with a moving average. It is widely used where repeated
forecasts require the application of methods like sum – of – the – digits and
trend adjustment methods. WMA may be expressed mathematically as:

Where:
= weight assigned in a particular period
= demand for the period
EXPONENTIAL SMOOTHING
- Is a continuous adjustment process. The alpha is used as the smoothing
parameter to minimize the error and has a value of O to 1. This is adjusted until the
minimized mean squared error(MSE)is solved. If the difference between the actual
value and forecasted value is negative, a lower must be assigned. A higher means that
greater weight is given to the most recent data and less weight to the distant past.

The formula for exponential smoothing is:

Where:
new = exponentially smoothed average to be used as the forecast
old = most recent actual data
old = most recent smoothed forecast
α = smoothing constant
The formula for MSE is:
MSE =
Where:
= the number of observations used to determine the initial forecast.

TREND PROJECTION
-This technique composed a series of historical data points that projects the
line into the future for medium-to-long-range forecasts. This kind of technique
only visualizes the relationship between the given variables. This approach
resulted in a straight line that minimizes deviations between the observed values
and the predicted values. The changes or errors are the vertical distances between
the observed values and the predicted values.
ASSOCIATIVE MODELS
-The example is a linear regression, incorporates the variables or factors that influence the
numbers which are being forecasted.

LINEAR REGRESSION
-It shows the relationship between two variables: the dependent and the independent. The
use of the mathematical model employed in the least-squares method of trend projection can be
used to perform a linear regression analysis. The dependent variables to be forecasted will still
be Y. But now the independent variable (x) no longer represents the time.

A least-squares line is described in terms of its у-intercept (the height at which it

intercepts the у-axis and its slope (the angle of the line).

If the у-intercept and slope can be computed, the line can be expressed with the following
equations.

Ƴ = α + bx
Where:
Ƴ= computed value of the variable to the predicted (called the dependent variable)
α= у-axis intercept
b= slope of the regression line (or the rate of exchange in у for a given change in s)
x= independent variable (in this case, time)

Satisfaction has developed equations that can be used to find the values of α and b for any
regression line. The slope b is found with the formula.

Where:
b= slope of the regression line
α= summation sign
χ= known values of the independent variable
Ƴ= known values of the dependent variable
 χ= average of the value of the x’s
у= average of the value of у’s
n= number of data points or observations

CORRELATION COEFFICIENTS FOR REGRESSION LINES

-The regression equation is one way of showing the nature of the relationship
between two variables. This will relates the value and changes to the other variable. To
evaluate the relationship between two variables by computing the coefficients of
correlation. This measure expresses the degree of strengths of the linear relationships.
Usually identified as x the coefficient of correlation can be any number between +1 and -
1.

To compare for r, the same data needed earlier will be used to calculate α and b for
the regression line. The rasher lengthy equation for r is:
 To compare for the coefficient of correlation for the data shown, an
additional column is needed to calculate for . The equation is then applied for .

2.0 1.0 1.0 2.0 4.0

3.0 3.0 9.0 9.0 9.0
2.5 4.0 16.0 10.0 6.3
2.0 2.0 4.0 4.0 4.0
2.0 1.0 1.0 2.0 4.0
3.50 7.00 49.00 24.50 12.25
The of appears to be a significant correlation and helps confirm the
relationship between the two variables.