PHILADELPHIA UNIVERSITY OF MEXICO

PAPANTLA CAMPUS

ESSAY ON FORECAST IN BUSINESS

PRESENTS:
URIEL ALFONSO VEGA SANTIAGO

TEACHING:
PROF. Joaquin Batiza Espinoza

DIPLOMA IN:
MANAGEMENT SKILLS AND BUSINESS INNOVATION

Papantla de Olarte See 25/April/2020

INTRODUCTION
This essay refers to the topic of business forecasting, starting from its
definition, some characteristics and some positions of certain authors.
Reference is made to the importance of predicting the uncertain nature of
business trends, this helps both administrators and managers to make better
plans and make better decisions.
In today's globalized world and with markets as competitive as those we face,
companies are forced to seek greater efficiency in their business processes.
A topic of current interest is how to more accurately forecast the demand for
products or services. More and more companies are redefining and
formalizing their forecasting process to achieve better sales and operational
planning and, therefore, better financial performance.
When a bad forecast is made, planning falls apart and all areas of the
company become inefficient. This can be seen directly in the company's poor
financial performance. Denied sales, excess inventories of products that
customers do not require, reduction of margins when selling at discounts to
achieve objectives, higher costs in purchasing, production and/or distribution
to react to emergencies, etc., these are the symptoms. Forecasting demand
with good accuracy is usually not easy. There are no recipes for how to do
this and each company has to determine the best way to prepare its
forecasts.

FORECASTS IN BUSINESS
What are Forecasts?
The forecast is not a prediction of what will inevitably happen in the future. A
forecast is information with a certain degree of probability of what could
happen. The probability of success is directly dependent on the preparation of
the forecasts. In other words, the result of the company's planning and
operation is directly linked to the certainty of the forecasts.
The basic objective of forecasting is to reduce the range of uncertainty within
which to make decisions that affect the future of the business and all the
parties related to it, because for a company, it is important to make a series of
related decisions of the same objective, because you have a work team many
times, but in fact only 50% of people have realized their potential, while the
other 50% have not committed.
When organizational managers are faced with the need to make decisions in
an uncertain atmosphere, what types of forecasts can they obtain? First,
long-term or short-term forecasting procedures must be classified. Long-term
forecasts are necessary for the overall process of establishing the
organization over the long term; therefore, they become the focus of senior
management. Short-term forecasts are used to design immediate strategies
and are used by first-line and middle managers to meet short-term needs.
Prediction can also be classified according to its position in the
microenvironment, that is, according to the degree of intervention of small
details and large added values. For example, a factory manager may be
interested in predicting the number of workers needed in the coming months,
while the federal government has forecast the number of employees
nationwide. Similarly, different levels of management in an organization tend
to focus on different levels of the micro and macro environment.
Prediction programs can also be classified according to their tendency to be
quantitative or qualitative. In an extreme case, a purely qualitative technique
is one that requires no manipulation of public data and uses only the
"judgment" of the predictor. Of course, even here, the forecaster's "judgment"
is actually the result of psychological manipulation of past historical data.
At the other extreme, pure quantitative techniques do not require any
evidence. They are mechanical programs that produce quantitative results. Of
course, certain quantitative processes require much more complex data
manipulation than others.
All formal forecasting procedures involve extending past experience into an
uncertain future. Therefore, except for those variables that are clearly
identified by the predictive model, the conditions generating the past data are
indistinguishable from future conditions.
For example, if you want to predict the performance index of employees at
work and you only use the entrance exam score as a prediction, then assume
that everyone's job performance index is only affected by the test. Taking into
account the inability to meet past and future assumptions, unless the
forecaster believes it has been modified, will lead to inaccurate predictions.
Forecasting technology can handle the approval of data generated in past
historical events resulting in the determination of four steps in the forecasting
process:
 Data collection.
 Data reduction or compression.
 Model construction.
 Extrapolation of the model (the prediction itself)
One of the most difficult and time-consuming parts of forecasting is collecting
valid and reliable data.
To determine whether data is useful, four conditions can be applied:
 Data must be reliable and accurate. Care must be taken while
collecting data, which should be from a reliable source and special
care must be taken for its accuracy.
 Data must be relevant. They must represent the environment to be
used. The company's history is supposed to represent data on past
cyclical economic activity.
 The data must be consistent. When reviewing definitions related to
data collection methods, adjustments should be made to maintain
consistency with historical patterns.
 Data must be periodic. Data collected, aggregated and published
regularly will be of great value to forecasters.
In general, there are two types of data that the predictor is interested in. The
first is data collected at a single point in time (one hour, one day, one week,
one month, or four months). The purpose is to examine the data and then
extrapolate or extend the revealed relationship to a larger population.
Instead, companies collect data values that are of interest to many
businesses every day, month, quarter, or year. In this case, time series data
will be collected. Analyze time series to discover patterns of past growth and
change, which can be used to predict future patterns and the needs of
ongoing businesses.
Data sources can be divided into primary and secondary. Secondary data
source is published data, and its collection purpose is not a specific forecast
or research purpose. Such data can be classified into internal sources from
within the organization or external sources generated from outside the
organization. Census-based publications are a good example of external
secondary sources. Accounting records are often used as sources of internal
auxiliary data.
Primary data sources include all methods of raw data collection. Such data
are usually collected through sampling procedures, focus group surveys, or
comprehensive surveys of items of interest. More common are weekly,
monthly, quarterly or annual records of key company variables.
The following aspects are considered among the representative variables to
be considered for generating forecasts:
 Consumption or Sales History: Allows you to consider a trend in the
movement of products, which may be linear, potential, logarithmic or
without trend.
 Current Inventory: This is essential, first-hand information, since it must
be forecast considering what companies have in stock, since the
objective is to use it.
 Pending Orders to Arrive: These are products that have not yet arrived
but that, once in the warehouse, are either intended to fulfill an order or
have simply been purchased as stock replenishment.
 Safety Stock (SS): It must be taken into account that the Safety Stock
(SS) depends on consumption and/or sales SS=f (Sale or
Consumption). It is not a fixed percentage amount that cannot be
changed in warehouses.
 Inventory Coverage: It is conditioned by the company policy (sales
levels or budget or cash availability, etc.). It is a variable considered in
many forecasts since it is the determinant between buying or not.
 Back Order and Back Log: These are variables that are similar in
themselves, since the first represents unfulfilled orders that are about
to expire and the second represents those that have already expired.
They are crucial when placing orders because once we have
inventory, it may disappear because no Back has been considered.
• Sales forecast for the Commercial area: This is very important when
generating forecasts because it is the target that the commercial area
estimates it can reach. We cannot ignore this information because it is the
sales force that has direct contact with customers, and it is fresh, top-line
information.
 CONCLUSION
The purpose of forecasting is to reduce the range of uncertainty over which
management judgment must be made. This purpose proposes two main rules
that the prediction process must follow:
Forecasts must be technically reasonable and produce accurate forecasts.
The forecasting procedure and its results must be effectively presented to the
department responsible for using the forecast in the company's decision-
making process; the results must also be justified in terms of their profitability.
Since the movement of resources and power within an organization is usually
based on predictions (forecasts) of the future, it is not surprising that a certain
amount of attractiveness occurs in the prediction process. This consideration
underlines the importance of the second main rule: decision makers must
understand and appreciate the predictions generated within the company so
that they can find their own way of managing it.
However, we must emphasize again that the combination of mechanical and
data processing procedures must use elements of judgment and common
sense. Only in this way can an intelligent prediction be made.

LITERATURE

https://www.freelibros.me/administracion/pronosticos-en-los-negocios-5ta-edicion-john-e-
hanke