Forecasting MCQ Quiz in বাংলা - Objective Question with Answer for Forecasting - বিনামূল্যে ডাউনলোড করুন [PDF]

Explanation:

Forecasting: 

Forecasting is the prediction of future sales or demand for a particular product in the market. Forecasts can be made by using the past data of a product.

It can be done in two ways

i) Qualitative Technique: 

• This approach is used for new product and used for long term forecasting. In this approach, there is no need for any data.

1. Opinion survey
2. Market trial
3. Market research
4. Delphi technique

ii) Quantitative Technique: 

• This is used to forecast the demand for the existing product for short term
• Here some previous data are given and based on that forecasting is done.

1. Simple Moving Average Method
2. Weighted Moving Average Method
3. Simple Exponential Smoothing Method
4. Trend Line Estimate or Linear Regression Method 

Critical Path Method:

• The critical path method (CPM) is a project modeling technique that’s used by project managers to find important deadlines and deliver a project on time.
• In a project, the critical path is the longest distance between the start and the finish, including all the tasks and their duration.

Concept:

Let the equation of regression line be

y = a + bx

∑y = na + b∑x     …... (1)

∑xy = a∑x + b∑x2   .....(2)

Calculation:

Given:

By Regression method:

∑y = na + b∑x

556 = 5a + 140b  ......(3)

∑xy = a∑x + b∑x2

17585 = 140a + 4394b  ......(4)

Solving (3) and (4)

a = -7.94 and b = 4.2552

The equation becomes

y = -7.94 + 4.2552x

For x = 60 lakh

y = -7.94 + (4.2552 × 60)

y = 247.372

As the demand was given in terms of 100 

∴ the demand for luxury cars is (247.372 × 100) = 24737.2

Concept:

When smoothing constant is given use the following formula to calculate the forecast.

Ft = α Dt-1 + (1 - α) Ft-1

Calculation:

Given:

D_t-1 = 73 units, F_t-1 = 78 units, α = 0.2

F_t = α D_t-1 + (1 - α) F_t-1 = α (Dt-1 - Ft-1) + Ft-1

F = 0.2 (73 – 78) + 78 = 77 units

Concept:

Forecasting is the prediction of future sales or demand for a particular product in the market. Forecasts can be made by using the past data of a product.

There are two types:

A) Qualitative or Subjective: It is for new products. This technique is for long-range forecasting.

• Opinion survey
• Market trial
• Market research
• Delphi technique

B) Quantitative or Objective: It is for old products. This technique is for short-range forecasting.

• Time series
  • Past average
  • Simple moving average
  • Weighted moving average
  • Exponential smoothing
• Econometric
  • Correlation
  • Regression

Explanation:

Trend line:

• Best - fit line is known as the trend line.
• It is generally used in the Linear regression analysis method of forecasting

• Linear Regression is a mathematical technique of obtaining the line of best fit between a dependent variable which is usually the demand of a product and any other variable on which demand is dependent.

• In regression analysis, the relationship between some independent variable x and dependent variable y  can be represented by a straight line Y = a + bx

where,

a = intercept on y-axis, b = slope of line

\(a=\frac{\sum y~-~b\sum x}{n}\)

\(b= \frac{n\sum (xy)~-~\sum x\sum y}{n\sum x^2~-~(\sum x)^2}\)

• Trendlines are easily recognizable lines that traders draw on charts to connect a series of prices together or show some data's best fit.

• The resulting line is then used to give the trader a good idea of the direction in which an investment's value might move.

• A trendline is a line drawn over pivot highs or under pivot lows to show the prevailing direction of price.

• Trendlines are a visual representation of support and resistance in any time frame.

• They show the direction and speed of price, and also describe patterns during periods of price contraction

• In terms of metrology, Best Fit Straight Line (BFSL) method is the relationship of the calibration curve to a calculated straight line that minimizes the error but does not pass through the endpoints.

Least square line:

• ​The Least Squares Regression Line is the line that makes the vertical distance from the data points to the regression line as small as possible. It’s called a “least square” because the best line of fit is one that minimizes the variance (the sum of squares of the errors). 

Endpoint line:

• End point method measures non-linearity when a straight line is drawn connecting the endpoints from P0 (zero differential pressure) to P_RS (full scale).  In this case, the end point accuracy is preserved when calibration adjustments are made to zero offsets or span

Terminal line:

• Relationship of a calibration curve to a specified straight line with end points at zero and full scale.

Concept:

By the exponential smoothing method:

\({F_t} = {F_{t - 1}} + \alpha \left[ {{D_{t - 1}} - {F_{t - 1}}} \right]\)

The moving average method uses the average of the most recent n data values in the time series as the forecast for the next period.

\({F_{t + 1}} = \frac{{{D_t} + {D_{t - 1}} + \ldots + {D_{t - n + 1}}}}{n}\)

Note that the n past observations are equally weighted.

Calculation:

By moving average method

Forecast for the fifth year

\({F_5} = \frac{{880~ + ~870~ +~ 890}}{3} = 880\;units\)

Now by exponential smoothing method

\({F_5} = {F_4} + \alpha \left( {{D_4} - {F_4}} \right)\)

880 = 876 + α (890 – 876)

14α  = 4

\(\Rightarrow \alpha = \frac{2}{7}\)

Concept:-

Simple exponential method -

This forecasting method is the most widely used of all forecasting techniques.

The simple exponential forecasting method has the formula for getting the forecasted value as,

F_t+1 = F_t + α(D_t - F_t) ​   .......Eqn(1)

Where

F_{t +1} = Forecasted value of time series at time t+1

F_t = Forecasted value of time series at time t

D_t = Actual value of time series at time t

α = Smoothing constant 

Given:-

F_t = 84, D_t = 79, α = 0.25, F_{t +1} =?

Calculation:-

By using equation (1), 

 Ft+1 = Ft + α(Dt - Ft) ​

F_t+1 = 84 + 0.25(79-84) = 84 - 1.25 = 82.75

F_t+1 = 82.75

Explanation:

• The sensitivity of forecast in simple moving average forecasting method, for the increase of the length of average period, decreases but with a lagging trend.
• In this method past data used for calculating moving average for constant period of time. The fresh average is computed at the end of each period by adding the actual demand data for the most recent period and deleting the data for older data.

• If we increase the period size, which means we are looking at data over a longer time period, it is likely that the data will be more smoothed out. This is because short-term fluctuations in the data will be averaged out over a longer time period. Therefore, if we increase the period size, the data will appear to be less volatile and more stable.

• However, this increased stability can come at the cost of decreased sensitivity. If we are looking at data over a longer time period, it may be more difficult to detect changes or trends in the data that occur over shorter time periods.

• Additionally, increasing the period size can also lead to lagging trends. This is because if we are looking at data over a longer time period, changes in the data may not be immediately apparent. Therefore, trends that are actually occurring may not be reflected in the data until later, which can result in a lag.

Additional Information Moving average Method: or rolling average Method: 

In this method, fresh average is calculated at the end of each period by adding the actual demand data for the most recent period and deleting the data for the order period. It gives equal weight to each of the most recent observations.

\({F_{n+1}} = \frac{{{D_1} + {D_2} + {D_3} + {D_4} + \ldots \ldots \ldots \ldots \ldots \ldots + {D_n}}}{n}\)

Weighted moving average Method: 

This method gives unequal weight to each demand data with more weight to recent data.

\({F_{n+1}} = \left[ {{w_{1}} \times {D_{1}} +{w_{2}\times {D_{2}}} +..........+ {w_{n}} \times {D_{n}}} \right]\)

Exponential Smoothing Method: 

This method gives weight to all the previous data and the pattern of weight assigned is exponentially decreasing in order with most recent data is given the highest weight.

In exponential smoothing method of forecast, the forecast for the next period is equal to 

Ft = α Dt-1 + (1 - α) Ft-1 

If we further expand the expression

Ft = α Dt-1 + (1 - α) (α Dt-2 + (1-α) Ft-2

Ft = α Dt-1 + α (1-α ) Dt-2 + (1 - α )2 Ft-2

• If smoothing coefficient (α) is 1 then the latest forecast would be equal to previous period actual demand.
• The technique is not simple as compared to moving average method.
• The technique is not simple as compared to moving average method.
• All observations are not assigned equal weightage.

Explanation:

In exponential smoothing method of forecasting weightage is given to the observations. Latest observation given maximum weightage and as the data get older, its weightage in the forecast keeps on decreasing.

Forecasting is defined as estimating the future value that a parameter will take. Most scientific forecasting methods forecast the future value using past data.

Some simple forecasting models using time series data are simple average, moving average and simple exponential smoothing.

Moving average Method: or rolling average Method: 

In this method, fresh average is calculated at the end of each period by adding the actual demand data for the most recent period and deleting the data for the order period. It gives equal weight to each of the most recent observations.

\({F_{n+1}} = \frac{{{D_1} + {D_2} + {D_3} + {D_4} + \ldots \ldots \ldots \ldots \ldots \ldots + {D_n}}}{n}\)

Weighted moving average Method: 

This method gives unequal weight to each demand data with more weight to recent data.

\({F_{n+1}} = \left[ {{w_{1}} \times {D_{1}} +{w_{2}\times {D_{2}}} +..........+ {w_{n}} \times {D_{n}}} \right]\)

Exponential Smoothing Method: 

This method gives weight to all the previous data and the pattern of weight assigned is exponentially decreasing in order with most recent data is given the highest weight.

In exponential smoothing method of forecast, the forecast for the next period is equal to 

Ft = α Dt-1 + (1 - α) Ft-1 

If we further expand the expression

Ft = α Dt-1 + (1 - α) (α Dt-2 + (1-α) Ft-2

Ft = α Dt-1 + α (1-α ) Dt-2 + (1 - α )2 Ft-2

• If smoothing coefficient (α) is 1 then the latest forecast would be equal to previous period actual demand.
• The technique is not simple as compared to moving average method.
• The technique is not simple as compared to moving average method.
• All observations are not assigned equal weightage.

Explanation:

Forecasting: 

Forecasting is the prediction of future sales or demand for a particular product in the market. Forecasts can be made by using the past data of a product.

It can be done in two ways

i) Qualitative Technique: This approach is used for new product and used for long term forecasting. In this approach, there is no need for any data.

Opinion survey:

• In this method, opinions are collected from the customer, retailer and distributor regarding the demand pattern of the product.

Market trial:

• It is applied for new product and in this case, a product is introduced between a limited population in the form of a free sample.
• It is applied for low-cost products like toothpaste, chocolate, coldrinks etc.

Market research:

• In this method, the work of survey is assigned to an external marketing agency and the purpose of the research is to collect information regarding the demand of a product and the various factors which influence the demand like customer income, location, quality, quantity etc are required to get the forecast.

Delphi technique:

• This technique is used to make more realistic judgemental methods by minimizing bias.
• In this method, a panel of experts is asked sequential questions. 
• It is the step by step procedure and the final forecast is obtained by the common opinion of all the experts.

ii) Quantitative Technique: This is used to forecast the demand for the existing product for short term

Here some previous data are given and based on that forecasting is done.

• Simple Moving Average Method
• Weighted Moving Average Method
• Simple Exponential Smoothing Method
• Trend Line Estimate or Linear Regression Method