The
first characteristic is,
Forecasts have to include both expected value and forecast errors.
Let
us take examples of paint companies X and Y and their forecast for the Vizag
city. The company X forecasted 1.2 lakh litres and one 17.8 lakhs litres of
paint per annum. The company Y forecasted 12 lakhs and 8 lakhs litres of paint
per annum. Both companies have 10 lakh litres per annum as the average demand.
However, the company X faces more uncertainty for getting better
forecasts. This uncertainty is popularly
known as a forecast error.
Second
forecasting characteristics is
The accuracy of the forecast is
better for shorter duration.
Let
me illustrate this with an Indian airline company, Indigo Airlines. Indigo
Airlines keep updating their travel plans by getting weather forecasting
Currently, Indigo Airlines is tied up with Indian Meteorological department for
supplying the weather data This will help the company in the capacity expansion
on a quarterly basis. The Ajatus software (https://www.ajatus.in/) that Indigo
uses brought fruitful results to the company. It improved Fleet assignment and
customized pricing on ancillaries such as leg rooms and meals
The
artificial intelligence Used by Indigo Airlines enhanced their revenue.
Indigo's forecasting included increasing aircraft seat availability and route
planning.
Third
characteristics of the forecasting is
aggregate forecasts are easier than Disaggregate forecasts.
Though,
many companies have their forecasting system in place, When they transform
their data with others in the supply chain
find forecast errors due to non collaboration This has made many
companies formulate their block chain with supply chain members. In this Block Chain,
the data is integrated across the supply chain. That improves the quality of
the data. The Ledger sharing and data security also improve the forecast across
the block chain Similarly, the forecasting of per capita income of India is much
easier than forecasting a Market Basket value of a customer coming to a retail
store.
Fourth characteristics of forecasting in supply chain is
Distortion in customer information effects company forecasting in the supply chain.
Retailers
who are very close to the customers forecasts better But as one moved up in a
supply chain to the distributor level, C&F level, manufacturers level and a
supplier level, the forecast error also
increases This is commonly known as the bullwhip effect. After the implementation
of CPFR and block chain technology in the supply chain, companies have
experienced reduction in the forecast errors
