Name Aleena Zafar

Sap id. 70135834

Section. A

Instructor. Mam Rida Akbar

Demand Forecasting Plan for Pak Elektron Limited (PEL)

Pak Elektron Limited (PEL) is a major manufacturer of home appliances in Pakistan. The
company is preparing to launch a new product line, including refrigerators and air conditioners.
To ensure effective production, inventory management, and cost optimization, PEL needs to
forecast demand for these products accurately over the next fiscal year. Below is a detailed
plan for how PEL can achieve this.

1. Choosing the Right Forecasting Method

For a more accurate demand forecast for PEL’s new product line, quantitative forecasting is
the ideal choice. This method uses historical data and statistical models to predict future
demand.

Recommended Forecas-ng Techniques:

• Time Series Forecasting

Time series forecasting is highly effective when historical demand data follows
recognizable patterns. For example, if PEL’s previous air conditioner sales in May-July
were consistently high due to seasonal demand, this method will help predict future
sales based on that pattern.

o Example Data: If PEL sold 1,200 air condi5oners in May last year, and a similar
pa<ern is expected this year, 5me series forecas5ng can predict sales for the
next fiscal year.
• Causal Forecasting (Regression Analysis)

This approach uses external variables (like economic conditions or promotional

activities) to predict demand. For example, if PEL plans a major promotional campaign,
regression analysis can predict how this will influence demand.

o Example Data: If a 10% increase in adver5sing results in a 5% increase in sales,

regression models can adjust forecasts accordingly.

By using quantitative methods, PEL ensures that predictions are based on hard data and are
free from personal bias.

2. Steps to Implement the Forecasting System

To implement an effective forecasting system, PEL should follow these steps:

Key Steps for Effec-ve Forecas-ng:

1. Data Collection (Step 1)

The first step is gathering historical data on sales, market trends, and any other variables
that could affect demand. PEL should focus on data like:

o Historical sales data (last 2–3 years for each product category)
o Promotional activity data (e.g., marketing spend and its effects on sales)
o Seasonal trends (e.g., peak demand months for air conditioners)
o Example Data: If in previous years, PEL’s refrigerator sales peaked by 15%
every December, this seasonal trend will be included in the forecast.

2. Data Analysis (Step 2)

Analyze the collected data to identify patterns and correlations. This will help PEL
decide which forecasting method to use.

o Example Data: A 12-month sales cycle for refrigerators reveals a peak demand
of 15% higher than average during the summer months.
3. Modeling the Forecast (Step 3)

Once patterns are identified, PEL can apply time series or causal methods to build a
forecast.

o Example Data: Using the last year’s monthly sales data, PEL could create a
forecast that predicts 1,000 units in January, rising to 1,200 units in June.

4. Monitoring and Adjusting Forecasts (Step 4)

PEL should track actual sales against forecasted values. If discrepancies occur, they can
adjust future forecasts.

o Example: If in April, actual sales were 1,150 units for air condi5oners (vs. the
forecast of 1,000 units), PEL should adjust the forecast for the following months
to reflect this trend.

By systematically collecting and analyzing data, PEL can build a more accurate forecasting
model, reducing errors in production planning and inventory management.
3. Operational Strategies Based on Forecasting

Once the forecasting system is implemented, PEL can optimize its operations and inventory
management to better align with expected demand.

Strategic Recommenda-ons for PEL:

1. Production Planning (Recommendation 1)

Accurate forecasts allow PEL to adjust production schedules and avoid overproduction
or shortages.

o Example Data: If the forecast predicts a demand of 1,000 refrigerators in

February, PEL can plan produc5on to meet this demand precisely, avoiding the
cost of overproduc5on.

2. Inventory Management (Recommendation 2)

Forecasting helps PEL maintain an optimal inventory level, preventing stockouts while
minimizing storage costs.

o Example Data: If the forecast predicts a total of 12,000 air condi5oners to be

sold in the next fiscal year, PEL can maintain an inventory level of 2,000 units
at any given 5me, ensuring product availability while avoiding overstock.

3. Supply Chain Coordination (Recommendation 3)

PEL can ensure timely procurement of raw materials by aligning supplier orders with
forecasted demand.

o Example Data: If the forecast indicates that refrigerator sales will rise by 10%
during the summer, PEL can order the required raw materials in advance to
meet produc5on needs.

By integrating forecasting into production and inventory planning, PEL can minimize
inefficiencies and reduce operating costs.
4. How to Revise Forecasts Based on Market Changes

The market is dynamic, and PEL must be prepared to adjust its forecasts in response to
significant shifts. This flexibility ensures that PEL can quickly adapt to changes and make
informed decisions.

When and How to Revise Forecasts:

1. Short-Term Adjustments (Revision 1)

When actual sales deviate from the forecast, PEL should adjust its forecasts to reflect
the new trend.

oExample Data: If the actual sales for air condi5oners in March are 1,200 units
(compared to a forecast of 1,000), PEL should increase the forecast for the
upcoming months to reflect this growth.
2. Long-Term Adjustments (Revision 2)

In cases of major disruptions or market changes, such as a competitor introducing a

new product, PEL should revise the forecast accordingly.

oExample Data: If a compe5tor’s new air condi5oner lowers market prices by

20%, PEL may need to lower its forecast by 15% to remain compe55ve.
3. Scenario Planning (Revision 3)

PEL can prepare for various possible outcomes using scenario planning, adjusting the
forecast based on the most likely market conditions.

o Example: PEL can prepare for three scenarios—best case, worst case, and most
likely case—and adjust its produc5on accordingly.

By staying proactive and revising forecasts in response to new data, PEL can maintain better
control over production and inventory.

Summary with Numbers:

• Forecas0ng Demand: Using past data, PEL can forecast monthly demand, e.g., 1,000
units in January and 1,200 units in June.
• Produc0on Planning: Align produc5on schedules with forecasts to meet demand, like
ensuring the manufacture of 1,000 refrigerators in February.
• Inventory Management: Maintain an op5mal inventory, such as 2,000 air condi0oners
in stock at any given 5me.
• Forecast Revisions: Adjust forecasts based on real-5me sales and market changes, e.g.,
revising a forecast of 1,000 air condi0oners to 1,200 units in March.