Idea Transcript
PEMP-EMM2506
Demand forecasting & Aggregate planning in a Supply chain
Session Speaker Prof.P.S.Satish M.S Ramaiah School of Advanced Studies - Bangalore
1
PEMP-EMM2506
Introduction • Forecasting provides an estimate of future demand • Factors that influence demand and whether these factors will continue to influence demand must be considered when forecasting. • Improved forecasts benefit all trading partners in the supply chain. • Better forecasts result in lower inventories, reduced stock-outs, smoother production plans, reduced costs, and improved customer service. Walmart’s Strategy M.S Ramaiah School of Advanced Studies - Bangalore
4
PEMP-EMM2506
Demand Planning and Forecasting Demand Planning • Involves forecasting and other activities like Promotion etc.
Types: 1. Independent Demand ( Ex: Finished goods) 2. Dependent or Derived Demand (Ex: components or subassemblies) • Independent Demand items are forecasted whereas the Dependent items can be derived from the latter
100 Refrigerators = 100 Compressors M.S Ramaiah School of Advanced Studies - Bangalore
9
PEMP-EMM2506
Approach to Demand Forecasting • Understand the Objective of Forecasting • Integrate Demand Planning and forecasting • Identify factors that influence demand forecast viz Demand, Supply and Product Side • Understand and Identify customer segments • Determine the appropriate forecasting technique • Establish Performance and error measures for the forecast.
M.S Ramaiah School of Advanced Studies - Bangalore
10
PEMP-EMM2506
Classification of Forecasting • Short range ( up to 1 year )
• Medium range ( up to 3 years ) • Long range ( more than 3 years )
M.S Ramaiah School of Advanced Studies - Bangalore
12
PEMP-EMM2506
Forecasting Types • Economic Forecast – IMF
• Technological Forecast – Euro Engines • Demand Forecast – Matching Supply and Demand
M.S Ramaiah School of Advanced Studies - Bangalore
13
PEMP-EMM2506
Forecasting Techniques • Qualitative forecasting is based on opinion and intuition. • Quantitative forecasting uses mathematical models and historical data to make forecasts. • Time series models are the most frequently used among all the forecasting models.
M.S Ramaiah School of Advanced Studies - Bangalore
14
PEMP-EMM2506
Forecasting Techniques- Cont. Qualitative Forecasting Methods Generally used when data are limited, unavailable, or not currently relevant.
Forecast depends on skill and experience of forecaster(s) and available information.
Four qualitative models used are: 1. 2. 3. 4.
Jury of executive opinion Delphi method Sales force composite Consumer survey M.S Ramaiah School of Advanced Studies - Bangalore
15
PEMP-EMM2506
Forecasting Techniques- Cont. Quantitative Methods • Time series forecasting- based on the assumption that the future is an extension of the past. Historical data is used to predict future demand. • Associative (causal) forecasting- assumes that one or more factors (independent variables) predict future demand. It is generally recommended to use a combination of quantitative and qualitative techniques.
M.S Ramaiah School of Advanced Studies - Bangalore
16
PEMP-EMM2506
Quantitative Methods • Moving Average Method • Exponential Smoothing • Trend Projection
Time series model
• Linear Regression
Causal model
M.S Ramaiah School of Advanced Studies - Bangalore
17
PEMP-EMM2506
Forecasting Techniques- Cont. Components of Time Series- Data should be plotted to detect for the following components: – Trend variations: either increasing or decreasing
– Cyclical variations: wavelike movements that are longer than a year – Seasonal variations: show peaks and valleys that repeat over a consistent interval such as hours, days, weeks, months, years, or seasons
– Random variations: due to unexpected or unpredictable events M.S Ramaiah School of Advanced Studies - Bangalore
18
PEMP-EMM2506
Forecasting Techniques- Cont. Time Series Forecasting Models – Simple Moving Average Forecasting Model. Simple moving average forecasting method uses historical data to generate a forecast. – Works well when demand is fairly stable over time.
M.S Ramaiah School of Advanced Studies - Bangalore
19
PEMP-EMM2506
Moving Average Method Calculations
M.S Ramaiah School of Advanced Studies - Bangalore
20
PEMP-EMM2506
Sales of Washing Machine at Arvee Electronics
M.S Ramaiah School of Advanced Studies - Bangalore
21
PEMP-EMM2506
Forecasting Techniques- Cont.
M.S Ramaiah School of Advanced Studies - Bangalore
22
PEMP-EMM2506
Forecasting Techniques- Cont. Time Series Forecasting Models – Weighted Moving Average Forecasting ModelWhenever there is a detectable trend or pattern, in order to be responsive, weights can be used.
M.S Ramaiah School of Advanced Studies - Bangalore
23
PEMP-EMM2506
M.S Ramaiah School of Advanced Studies - Bangalore
24
PEMP-EMM2506
M.S Ramaiah School of Advanced Studies - Bangalore
25
PEMP-EMM2506
Forecasting Techniques- Cont.
M.S Ramaiah School of Advanced Studies - Bangalore
26
PEMP-EMM2506
Disadvantage of moving average • Lengthy calculations involved • Need to keep historical Data • Equal weightage or no basis for weightage for the Data To overcome these difficulties, exponential smoothing is used
M.S Ramaiah School of Advanced Studies - Bangalore
27
PEMP-EMM2506
Forecasting Techniques- Cont. Time Series Forecasting Models – Exponential Smoothing Forecasting Model- a weighted moving average in which the forecast for the next period’s demand is the current period’s forecast adjusted by a fraction of the difference between the current period’s actual demand and its forecast. – Only two data points are needed. Ft+1 = Ft+(At-Ft) Where Ft+1 = forecast for Period t + 1 Ft = forecast for Period t At = actual demand for Period t = a smoothing constant (0 ≤ ≤1).
= 2/(N+1) Where N= period of moving average ; Typically 0.1 to 0.4
M.S Ramaiah School of Advanced Studies - Bangalore
28
PEMP-EMM2506
M.S Ramaiah School of Advanced Studies - Bangalore
29
PEMP-EMM2506
Forecasting Techniques- Cont.
M.S Ramaiah School of Advanced Studies - Bangalore
30
PEMP-EMM2506
Trend Projections
Least square method for finding the best-fitting line M.S Ramaiah School of Advanced Studies - Bangalore
31
PEMP-EMM2506
Least Square Method
M.S Ramaiah School of Advanced Studies - Bangalore
32
PEMP-EMM2506
An Example
M.S Ramaiah School of Advanced Studies - Bangalore
33
PEMP-EMM2506
M.S Ramaiah School of Advanced Studies - Bangalore
34
PEMP-EMM2506
Seasonal Variations in Data • Monthly sales and demand of IBM notebook computer in Bangalore is as shown below for 1999-2000. Calculate 2001 demand for selling 1200 notebooks. Month
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Sale 1999
80
75
80
90
115
110
100
90
85
75
75
80
Demand 2000
100
85
90
110
131
120
110
110
95
85
85
80
M.S Ramaiah School of Advanced Studies - Bangalore
35
PEMP-EMM2506
Create a table in this format Month
Sale 1999
Demand 2000
Avg. 1999-2000
Avg. Monthly Demand
M.S Ramaiah School of Advanced Studies - Bangalore
Avg. Seasonal Index
36
PEMP-EMM2506
M.S Ramaiah School of Advanced Studies - Bangalore
37
PEMP-EMM2506
IBM Notebook exercise … Contd
M.S Ramaiah School of Advanced Studies - Bangalore
38
PEMP-EMM2506
M.S Ramaiah School of Advanced Studies - Bangalore
39
PEMP-EMM2506
Causal Forecasting Model -Regression Analysis
M.S Ramaiah School of Advanced Studies - Bangalore
40
PEMP-EMM2506
Causal Forecasting Model • Consider’s several variables that are related • Explain’s cause of time series Ex: Sale of a product depends on: Firm’s Advertising budget Price charged Competitor’s price Promotional Strategies etc. • Regression Analysis is a tool to develop causal model
M.S Ramaiah School of Advanced Studies - Bangalore
41
PEMP-EMM2506
Forecasting Techniques- Cont. Associative Forecasting Models- One or several external variables are identified that are related to demand – Simple (linear) regression. Only one explanatory variable is used and is similar to the previous trend model. The difference is that the x variable is no longer a time but an explanatory or independent variable. Ŷ = a + b1 x – where Ŷ = forecast or dependent variable x = explanatory or independent variable a = y-axis intercept of the line b1 = slope of the line M.S Ramaiah School of Advanced Studies - Bangalore
42
PEMP-EMM2506
Forecasting Techniques- Cont. Associative Forecasting Models– Multiple regression. Where several explanatory variables are used to make the forecast. Ŷ = a + b1x1 + b2x2 + . . . bkxk – where Ŷ = forecast or dependent variable xk = kth explanatory or independent variable a = Y-axis intercept of the line bk = regression coefficient of the independent variable xk M.S Ramaiah School of Advanced Studies - Bangalore
43
PEMP-EMM2506
M.S Ramaiah School of Advanced Studies - Bangalore
44
PEMP-EMM2506
Scatter Diagram M.S Ramaiah School of Advanced Studies - Bangalore
45
PEMP-EMM2506
M.S Ramaiah School of Advanced Studies - Bangalore
46
PEMP-EMM2506
M.S Ramaiah School of Advanced Studies - Bangalore
47
PEMP-EMM2506
Forecast Accuracy The formula for forecast error, defined as the difference between actual demand and the forecast, follows: Forecast error, et = At - Ft where et = forecast error for Period t At = actual demand for Period t Ft = forecast for Period t Several measures of forecasting accuracy follow: – Mean absolute deviation (MAD)- a MAD of 0 indicates the forecast = predicted demand.
= ∑ (forecast error) / n, where n is number of period. M.S Ramaiah School of Advanced Studies - Bangalore
48
PEMP-EMM2506
Formulae for Monitoring and Controlling forecast • MAD = ( Sum of forecast errors / n ). • Mean squared error (MSE) = ( ( Sum of forecast error ) 2 / n ).
M.S Ramaiah School of Advanced Studies - Bangalore
49
PEMP-EMM2506
Aggregate Planning
50
PEMP-EMM2506
Introduction
• Aggregate planning is done for period of 6 to 18 months • It translates business plan and strategic intent to operational decisions • Purpose is to specify combination of production rate, workforce and inventory in hand needed • In planning total expected demand is reckoned without regard to product mix that makes up the figure 51
PEMP-EMM2506
Aggregate Planning • What is it? – Once long term decisions are made, it is necessary to make intermediate range plans that are consistent with long-range policies – Management must work within the resources allocated by long-range decisions – Given the sales forecasts, the factory capacity, aggregate inventory levels, and the size of the workforce, the manager must decide at what rate of production to operate the plant over the intermediate term – This intermediate-range planning is generally known as aggregate planning
52
PEMP-EMM2506
Why Aggregate Planning is necessary? • Fully load facilities and minimize overloading and underloading • Make sure enough capacity available to satisfy expected demand • Plan for the orderly and systematic change of production capacity to meet the peaks and valleys of expected customer demand • Get the most output for the amount of resources available 53
PEMP-EMM2506
Why Aggregate Planning necessary? • To meet demand fluctuations like in festivals • Capacity fluctuations – Number of working days in month, unexpected shutdowns.. • Production rate cannot be changed without proper planning • Planning helps to manage anticipated demand
54
PEMP-EMM2506
Aggregate Planning • Purpose – Aggregate plans and master schedules provide common points at which capacity and inventories are considered jointly in the light of firm’s longrange plans, and they provide inputs to the financial plan, the marketing plan, and requirements planning and detailed scheduling decisions – Several crucial decisions have to be made while generating an aggregate plan • Management may ask many inventory- and workforce- related questions • To what extent should inventories be used for absorbing changes in demand that might occur during the intermediate term? • Should we absorb the fluctuations by varying the size of the workforce*
– Generally a mixture of strategies is preferred and is feasible – An aggregate plan is a valuable procedure to help in the development of operating budgets 55
PEMP-EMM2506
Aggregate Planning • Purpose – Products or services can be aggregated into a set of relatively broad product families without getting into too much of detail – A company can organize labour in various ways – based on flexibility to handle different products/services, or, based on product lines – When time is considered, the planning horizon is an important aspect. It is the length of time covered by an aggregate plan. A company will usually look at time in the aggregate – months, quarters, or seasons (rather than days or hours) – Some companies use monthly planning periods for the near portion of the planning horizon and quarterly periods for the later portion 56
PEMP-EMM2506
Aggregate Planning • Purpose – In practice, planning periods reflect a balance between the needs for • a limited number of decision points to reduce planning complexity • flexibility to adjust output rates and the workforce levels when demand forecasts exhibit seasonal variations • Relationship of aggregate to other plans is in figure below
Business or Annual plan Aggregate plan MPS or Workforce schedule
57
PEMP-EMM2506
Aggregate Planning • Managerial inputs from various functional areas to aggregate plans Operations Current, future & workforce capacities
Materials Supplier capabilities Storage capacity Materials availability
Distribution and Marketing Customer needs, Demand, Competition
Aggregate plan
Accounting and Finance Cost data, financial Condition of firm
Human resources Labour market Conditions, training capacity
Engineering New products, design changes machine standards
58
PEMP-EMM2506
Aggregate planning process • The process for preparing aggregate plans is dynamic and continuing, as aspects of the plan are updated periodically when new information becomes available and new opportunities emerge* • The steps are: – – – –
Determining demand requirements Identifying alternatives, constraints and costs Preparing an acceptable plan Implementing and updating the plan
59
PEMP-EMM2506
Aggregate planning process • The process flow chart Determine requirements for planning horizon
Identify alternatives, constraints and costs
Prepare prospective plan for planning horizon
No Move ahead to Next planning session
Implement and update the plan
Is the plan acceptable? Yes 60
PEMP-EMM2506
Aggregate planning process • Determining demand requirements – The first step in the planning process is to determine the demand requirements for each period of the planning horizon – For production plans, the requirements represent the demand for finished goods and the external demand for replacement parts – For staffing plans, the planner bases forecasts of staff requirements for each workforce group on historical levels of demand, managerial judgment and existing backlogs for services 61
PEMP-EMM2506
Aggregate planning process • Identifying alternatives, constraints and costs – Constraints represent physical limitations or managerial policies associated with the aggregate plan • Examples of physical constraints might include training facilities capable of handling only so many new hires at a time, machine capacities that limit maximum output, or inadequate inventory storage space
– A planner usually considers several types of costs when preparing aggregate plans • Regular-time costs • Overtime costs – typically 150% of regular time wages • Hiring (advertising jobs, interviews, etc.) and layoff (exit interviews, severance pay, etc.) costs 62
PEMP-EMM2506
Aggregate planning process • Identifying alternatives, constraints and costs – A planner usually considers several types of costs …. • Inventory holding costs that vary with the level of inventory investment: the costs of capital tied up in inventory, variable storage and warehousing, etc. • Backorder and stock out costs like the costs of lost sales and the potential cost of losing the customer’s sales to competitors • Hiring (advertising jobs, interviews, etc.) and layoff (exit interviews, severance pay, etc.) costs – Preparing an acceptable plan • This is an iterative process (plans may need to go through several revisions and adjustments
– Implementing and updating the plan which requires the commitment of all functional area managers 63
PEMP-EMM2506
Aggregate planning process • Developing and evaluating the level production plan – One possible level strategy, which uses a constant number of employees that will satisfy demand during the planning horizon, is determined by using the maximum amount of overtime in the peak period – Under time is used in slack periods – Level strategy can lead to considerable under time – Cost of this unused capacity depends on whether under time is paid or unpaid – The planning can be done with a spreadsheet^ – Example problem follows 64
PEMP-EMM2506
Aggregate planning • Details – A manufacturing firm’s aggregate plan, called a production plan focusses on production rates and inventory holdings – A service firm’s aggregate plan, called a staffing plan, centers on staffing and other labour related factors – Based on the long-term goals of a company, the aggregate plan specifies how the company will work for the next year or so toward these goals within existing equipment and facility capacity constraints – For manufacturing companies, the aggregate plan links strategic goals and objectives with production plans for individual products and the specific components that go into them 65
PEMP-EMM2506
Aggregate Planning • Details – For service firms the aggregate plan links strategic goals with detailed workforce schedules – When we say aggregate, the sense is that the planning activities at this early stage are concerned with homogeneous categories, such as gross volumes of products or number of customers served – Illustration below gives the aggregate plan of a motor manufacturer
66
PEMP-EMM2506
Aggregate planning • Strategies – Many aggregate planning strategies are available to the manager – The many functional areas in an organization that give input to the aggregate plan typically have conflicting objectives for the use of the organization’s resources – The objectives could be: • Minimize costs/maximize profits – If customer demand is not affected by the plan, minimizing costs will also maximize profits • Maximize customer service – Improving delivery time and on-time delivery may require additional workforce, machine capacity, or inventory resources • Minimize inventory investment – Inventory accumulations are expensive because the money could be used for more productive investments • Maximize utilization of plant and equipment – Processes based on a line flow strategy require uniformly high utilization of plant and equipment 67
PEMP-EMM2506
Aggregate planning • Strategies – The objectives (cont’d): • Minimize changes in production rates – Frequent changes in production rates can cause difficulties in coordinating the supplies of materials and require production line rebalancing • Minimize changes in workforce levels – Fluctuating workforce levels may cause lower productivity because new employees typically need time to become fully productive
– Balancing these various objectives to arrive at an acceptable aggregate plan involves consideration of various alternatives – A classification scheme is shown in the next slide 68
PEMP-EMM2506
Aggregate planning-Meeting Demand • Pure Strategy : One of the variable say workforce is changed to absorb demand fluctuation • Mixed Strategy : Here more than one variable say workforce and inventory are changed to absorb fluctuations This is mostly used in Industries
69
PEMP-EMM2506
Aggregate planning-Meeting demand • Chase Strategy : Match the production rate needed by hiring and laying off employees as the order rate varies. For this pool of trained people must be available as volume increases. Has motivational issues.
70
PEMP-EMM2506
Aggregate planning-Meeting Demand • Level Strategy : Making a stable workforce working at constant output rate. Shortages and surpluses are absorbed by fluctuating inventory levels, order backlogs and lost sales. Potential implication decreased customer service level and increased inventory costs
71
PEMP-EMM2506
Aggregate Planning-Meeting Demand • Stable workforce – Variable work hours : Vary the output by varying number of hours worked through flexible work schedules or overtime. Better employee motivation. Overtime cost extra
72
PEMP-EMM2506
Medium-Term Capacity Adjustments • Workforce level – Hire or layoff full-time workers – Hire or layoff part-time workers – Hire or layoff contract workers
• Utilization of the work force – Overtime – Idle time (under time) – Reduce hours worked
• . . . more 73
PEMP-EMM2506
Medium-Term Capacity Adjustments • Inventory level – Finished goods inventory – Backorders/lost sales
• Subcontract
74
PEMP-EMM2506
Aggregate Plans for services • For standardized services, aggregate planning may be simpler than in systems that produce products • For customized services, – there may be difficulty in specifying the nature and extent of services to be performed for each customer – customer may be an integral part of the production system • Absence of finished-goods inventories as a buffer between system capacity and customer demand
75
PEMP-EMM2506
Yield Management • It is a process of allocating right type of capacity to the right type of customer at the right price and time to maximize revenue or yield E.g. :- Airlines booking in advance at cheaper prices - Hotel booking in advance
76
PEMP-EMM2506
Yield Management Yield Management is most effective when : • Demand can be segmented by customer • Fixed costs are high and variable costs are low • Inventory is perishable • Product can be sold in advance • Demand is highly variable 77
PEMP-EMM2506
Session Summary •
Analysing demand forecasts has been explained
•
Time series and causal models have been demonstrated with examples.
•
Strategies adopted in aggregate planning has been elucidated
M.S Ramaiah School of Advanced Studies - Bangalore
80