Forecasting Models

Forecasting Models
Everyday a shop owner thinks how many items he would be able to sell.
The florist at the roadside keeps flower thinking in mind how much he would be able to sell by the end of the evening.
Here they are applying forecasting- albeit on a miniscule scale.
So we all forecast something each and every day.
What is Forecasting?
Planning is an important function of any management which based of forecasting. Hence, Forecasting is the art and science of predicting future events. Forecasts are required throughout an organization and at all levels of decision making in order to plan for the future and make effective decisions. The principal use of forecasts in operations management is in predicting the demand for manufactured products and services for time horizons ranging from several years down to 1 day. Depending on the planning horizon, forecasting can be classified in three ways:
Short – range forecasting (up to 1 year)
Medium – range forecasting ( up to 3 years)
Long – range forecasting (more than 3 years)
Types of forecasts
In general, a contemporary business organization employs three distinct types of forecasts.
These are given under:
1. Economic forecasts
2. Technological forecasts
3. Demand forecasts
Economic forecasts address the business cycle by predicting inflation rates, money supplies, housing starts, and other planning indicators.
Technological forecasts are concerned with rates of technological progress, which can result in the birth of exciting new products, requiring new plants and equipment.
Demand forecasts are projections of demand for a company’s products or services. These forecasts, also called sales forecasts, drive a company’s production, capacity, and scheduling systems and serve as inputs to financial, marketing, and personnel planning.
What is the strategic importance of forecasting?
Forecasting plays a very important role in the following areas:
Human resource management
Hiring, training and laying-off workers all depend on anticipated demand.
Capacity planning

Quantitative Methods
The chief Quantitative methods are:
1. Moving averages
2. Exponential smoothing Time series models
3. Trend projection
4. Linear regression  Causal model
The time series models of forecasting predict on the basis of the assumption that the future is a function of the past. In other words, they look at what has happened over a period of time and use a series of past data to make a forecast. If we are predicting weekly sales of washing machine, we use the past weekly sales for washing machine in making the forecast.
A causal model incorporates into the model the variables or relationships that might influence the quantity being forecast. A causal model for washing machine sales might include relationships such as new housing, advertising budget, and competitors’ prices.
Moving over to a structured approach to forecasting, let me introduce the basic steps involved in this process:-
Steps in Forecasting
There are eight steps to a forecasting system.
These are:
1. Determine the use of the forecast –
(What objectives are we trying to achieve?)
2. Select the items that are to be forecasted
3. Determine the time horizon of the forecast –
(Is it short, medium, or long – range?
4. Select the forecasting model
5. Gather the data needed to make the forecast
6. Validate the forecasting model
7. Make the forecast
8. Implement the results
We now focus our attention to one of the most widely used and effective method of forecasting.
Time Series Forecasting
A time series is based on a sequence of evenly spaced (weekly, monthly, quarterly, and so on) data points. Forecasting time series data implies that future values are predicted only from past values and that other variables, no matter how potentially valuable, are ignored.
Decomposition of a Time Series
There are four main ways of decomposing the time series:
􀂃 Trend
􀂃 Seasonality
􀂃 Cycles
􀂃 Random variations

QualitativeMethods:

Market Survey

Build-up forecast

Life cycle analog method

Panel consensus forecasting

Delphi method

Capacity management

Capacity management
What is Capacity?
Capacity is the maximum rate of output for a process. The operations manager must provide the capacity to meet current and future demand; otherwise, the organization will miss opportunities for growth and profits.
Capacity plans are made at two distinct levels:
Long term capacity plan –
( it covers at least two years in future.g. investment in new facilities and equipments)
Short term capacity –
(it covers week-to-week operation e.g. it focuses on workforce size, overtime budgets, inventories, etc)
The relevant questions in this regard are:
􀂃 How much of cushion is needed to handle variable, uncertain demand?
􀂃 Should we expand capacity before the demand is there or wait until demand is more certain?
Measures of capacity –
There are two main methods of measuring capacity. These are expressed as:
􀂃 Output measures (choice for high volume process)
􀂃 Input measures (choice for low volume flexible processes)
Output measures
Output measures are best utilized when the firm provides a relatively small number of standardized products and services, or when applied to individual process within the overall firm. Nissan Motor Company states capacity at its Tennessee plant as 4,50,000 vehicles per year. That plant produces only one type of vehicle, making capacity easy to measure. However, many organizations produce more than one product or service. For example, a restaurant may be able to handle 50 sit-down or 100 take-out customers per hour. It might also handle 25 sit-down and 50 take-out customers or many other combinations of the two types of customers. As the amount of customization and variety in the product mix becomes excessive, output-based capacity measures become less useful.
Input measures
Input measures are useful for low-volume, flexible processes. For example in a photocopy shop, capacity can be measured in machine hours or number of machines. Just as product mix can complicate output capacity measures, so as demand can complicate input measures. Demand, which is expressed as an output rate, must be converted to an input measure. Only after making the conversion can a manager compare demand requirements and capacity on an equivalent basis. For example, the manager of a copy center must convert its annual demand for copies from different clients to the number of machines required.
When we talk about capacity planning it requires knowledge of the current capacity of a process and its utilization.
My next question to you would be:-
What is capacity utilization?
Capacity utilization is the degree to which equipment, space, or labour is currently being used. It is expressed as a percent.
Mathematically, it can be expressed as under:
Utilization = %100capacity Maximumrateoutput Average×
The unit of measurement for both Numerator and Denominator should be same.
Utilization indicates the need for adding extra capacity or eliminating unneeded capacity.
Two definitions of maximum capacity, i.e.:
Peak capacity and
Eeffective capacity
are quite useful.
Let us focus on these aspects.
Peak capacity
The maximum output that a process or facility can achieve under ideal conditions is called peak capacity. It can be sustained only for a short time, few hours a day or few days in a month. A process reaches it by using marginal methods of production, such as excessive overtime, extra shifts, temporarily reduced maintenance activities, overshifts, and subcontracting.
Effective capacity
The maximum output that a process or firm can economically sustain under normal conditions is its effective capacity. In some organizations, effective capacity implies a one-shift operation; in others, it implies a three-shift operation. For this reason, Census Bureau surveys define capacity as the greatest level of output the firm can reasonably sustain by using realistic employee work schedules and the equipment currently in place.
When operating close to peak capacity, a firm can make minimal profits or even lose money despite high sales levels.
Let us now see how to calculate these measures of utilization through an example.
Example
If operated around the clock under ideal conditions, the fabrication department of an engine manufacturer can make 100 engines per day. Management believes that a maximum output rate of only 45 engines per day can be sustained economical over a long period of time. Currently, the department is producing an average of 50 engines per day. What is the utilization of the department relative to peak capacity? Effective capacity?
Solution.
The two utilization measures are
Utilizatio = peakncapacityPeakrateoutputAverage = 10050×100% = 50%
effectivenUtilizatio = capacityEffectiverateoutputAverage = 4550×100% = 111%
Note- Even though the fabrication department falls well short of the peak capacity, it is well beyond the output rate judged to be the most economical. Capacity expansion options could be evaluated.
To increase the maximum capacity the process need to be focused more. Most processes involve multiple operations, and often their effective capacities are not identical. A bottleneck is an operation that has the lowest effective capacity of any operation in the process and thus limits the system’s output. Figure 5.1 shows a process where operation 2 is a bottleneck, whereas Figure 5.2 shows the process when the capacities are perfectly balanced, making every operation a bottleneck.
A project or job process does not enjoy the simple line flows. Its operations may process many different items, and the demand on any one operation could vary considerably from one day to the next. Bottlenecks can still be identified by computing the average
Inputs
utilization of each operation. In this situation, management prefers lower utilization rate, which allow greater slack to absorb unexpected rise in demand. The long-term capacity of bottleneck operation can be expanded in various ways. Investments can be made in new equipments, The bottleneck’s capacity also can be expanded by operating it more hour per week, such as going from a one-shift operation to multiple shifts, or going from five workdays week to six or seven workdays per week. Managers also might relieve the bottleneck by redesigning the process, either through process reengineering or process improvement.
Theory of constraints (TOC) refers to an approach that focuses on bottlenecks of a firm’s financial performance.
Long-term capacity expansions are not the only way to ease bottlenecks. Overtime, temporary or part-time employees, or temporarily outsourcing during peak periods are short – term options. Managers should also explore ways to increase the effective capacity utilization at bottlenecks, without experiencing the higher costs and poor customer service usually associated with maintaining output rates at peak capacity.
The key is to carefully monitor short-term schedules, keeping bottleneck resources as busy as practical. They should also minimize the time spent unproductively for setups. When a changeover is made at a bottleneck operation, the number of units or customers processed before the next changeover should be large, compared to the number processed at less critical operations. Maximum the number processed per setup means that there will be fewer setups per year and thus less total time lost to set ups.
The TOC is an approach to management that focuses on whatever hinders progress toward the goal of maximizing the flow of total value – added funds or sales less sales discounts and variable costs. The impediments or bottlenecks might be overloaded processes such as order entry, new product development, or a manufacturing operation. The fundamental idea is to focus on the bottlenecks to increase their throughput, thereby increasing the flow of total value – added funds. .
Application of TOC involves the following steps
It’s basically a five step process.
1. Identify the system bottleneck
2. Exploit the bottleneck
3. Subordinate all other decision to step 2
4. Elevate the bottleneck
5. Do not let inertia set in
Factors that determine capacity
Ultimately, the output from a production facility or system is not determined simply by the physical size of the facility, the sizes or types of machines, or the number of employees working. Production capacity, especially effective capacity, is affected by the design of the products and processes, the training of employees, the management of quality, and many other factors. The most important factors affecting production capacity are:
1. Process design. In multistage production processes the maximum rate of output that can be achieved is governed by the slowest) lowest capacity stage.
2. Product design. With exactly the same personnel and equipment, the capacity for making a product that is well designed for production will be greater than for a poorly designed one.
3. Product variety. The fewer types of products made by a production unit and the more similar they are, the more specialized equipment and jobs can be, and the less time lost on product changeovers and machine set-ups.
4. Product quality. The way products are made, tested, and inspected will affect the rate at which products of acceptable quality can be produced.
5. Production scheduling. Scheduling that keeps product flows well balanced and synchronized and unproductive time minimized will utilize machines and personnel better and result in greater effective capacity.
6. Materials management. Shortages of materials can cause work stoppages, while excess inventories can cause congestion and wasted time searching for materials.
7. Maintenance. Equipment breakdowns and defects due to machine wear are two majors sources of lost production.
8. Job design and personnel management. The amount of output a production system actually produces is greatly determined by the personnel operating the system. Inadequate training, poor job design, overwork, and absenteeism all lead to lost production.

Design of product layouts

Design of product layouts
In product layout, equipment or departments are dedicated to a particular product line, duplicate equipment is employed to avoid backtracking, and a straight-line flow of material movement is achievable. Adopting a product layout makes sense when the batch size of a given product or part is large relative to the number of different products or parts produced
Assembly lines are a special case of product layout. In a general sense, the term assembly line refers to progressive assembly linked by some material handling device. The usual assumption is that some form of pacing is present and the allowable processing time is equivalent for all workstations. Within this broad definition, there are important differences among line types. A few of these are material handling devices (belt or roller conveyor, overhead crane); line configuration (U-shape, straight, branching); pacing (mechanical, human); product mix (one product or multiple products); workstation characteristics (workers may sit, stand, walk with the line, or ride the line); and length of the line (few or many workers). The range of products partially or completely assembled on lines includes toys, appliances, autos, clothing and a wide variety of electronic components. In fact, virtually any product that has multiple parts and is produced in large volume uses assembly lines to some degree.
Assembly-line systems work well when there is a low variance in the times required to perform the individual subassemblies. If the tasks are somewhat complex, thus resulting in a higher assembly-time variance, operators down the line may not be able to keep up with the flow of parts from the preceding work station or may experience excessive idle time. An alternative to a conveyor-paced assembly line is a sequence of workstations linked by gravity conveyors, which act as buffers between successive operations
Line balancing
Assembly-line balancing often has implications for layout. This would occur when, for balance purposes, workstation size or the number used would have to be physically modified.
The most common assembly line is a moving conveyor that passes a series of workstations in a uniform time interval called the workstation cycle time (which is also the time between successive units coming off the end of the line). At each workstation, work is performed on a product either by adding parts or by completing assembly operations. The work performed at each station is made up of many bits of work, termed tasks, elements, and work units. Such tasks are described by motion-time analysis. Generally, they are grouping that cannot be subdivided on the assembly line without paying a penalty in extra motions.
The total work to be performed at a workstation is equal to the sum of the tasks assigned to that workstation. The line balancing problem is one of assigning all tasks to a series of workstations so that each workstation has no more than can be done in the workstation cycle time, and so that the unassigned (idle) time across all workstations is minimized. The problem is complicated by the relationships among tasks imposed by product design and process technologies. This is called the precedence relationship, which specifies the order in which tasks must be performed in the assembly process.
The steps in balancing an assembly line are:
1. Specify the sequential relationships among tasks using a precedence diagram.
2. Determine the required workstation cycle time
3. Determine the theoretical minimum number of workstations Nt =
4. Select a primary rule by which tasks are to be assigned to workstations, and a secondary rule to break ties.
5. Assign tasks, one at a time, to the first workstation until the sum of the task times is equal to the workstation cycle time, or no other tasks are feasible because of time or sequence restrictions. Repeat the process for Workstation 2, Workstation 3, and so on until all tasks are assigned.
6. Evaluate the efficiency of the balance derived
7. If efficiency is unsatisfactory, rebalance using a different decision rule.
Process layout design
The analysis involved in the design of production lines and assembly lines relates primarily to timing, coordination, and balance among individual stages in the process. For process layouts, the relative arrangement of departments and machines is the critical factor because of the large amount of transportation and handling involved.
Procedure for designing process layouts
Process layout design determines the best relative locations of functional work centers. Work centers that interact frequently, with movement of material or people, should be located close together, whereas those that have little interaction can be spatially separated. One approach of designing an efficient functional layout is described below.
1. List and describe each functional work center
2. Obtain a drawing and description of the facility being designed
3. Identify and estimate the amount of material and personnel flow among work centers
4. Use structured analytical methods to obtain a good general layout
5. Evaluate and modify the layout, incorporating details such as machine orientation, storage area location, and equipment access.
The first step in the layout process is to identify and describe each work center. The description should include the primary function of the work center )drilling, new accounts, or cashier_; its major components, including equipment and number of personnel; and the space required. The description should also include any special access needs (such as access to running water or an elevator) or restrictions (it must be in a clean area or away from heat).
For a new facility, the spatial configuration of the work centers and the size and shape of the facility are determined simultaneously. Determining the locations of special structures and fixtures such as elevators, loading docks, and bathrooms becomes part
of the layout process. However, in many cases the facility and its characteristics are a given. In these situations, it is necessary to obtain a drawing of the facility being designed, including shape and dimensions, locations of fixed structures, and restrictions on activities, such as weight limits on certain parts of a floor or foundation.
To minimize transport times and material-handling costs, we would like to place close together those work centers that have the greatest flow of materials and people between them. To estimate the flows between work centers, it is helpful to begin by drawing relationship.

Service Process

Service Process
In planning manufactured products, a great deal of attention must be paid to technical specifications such as size, weight, and engineering specifications. For physical characteristics, standard may be determined and the conformance to these standards can be monitored for quality assurance. The quality of services, on the other hand, depends on the skill and training of personnel who produce the services. It is more difficult to set standards on performance, and consistent quality is more difficult to ensure.
For example, all meals on an airline may be of the same quality, but service may vary considerably with different flight crews.
Another important difference between manufactured products and services is that manufactured products can be stored for future use, whereas services must be made available to the customer on demand. This difference is another important consideration for quality assurance. That is, major quality considerations must be planned and designed into the service just as it should be with manufactured products; however, finished goods may be inspected prior to being released from the factory. For services, this cannot be done.
Additional considerations should be given when designing service products are as follows:
1. To what extent will the customer be involved in the process? For example, will a retail operation be primarily self-service (Big Bazaar)? Will a financial institution allow customers to execute their own transactions using automatic teller machines or telephones (Citibank)? Normally, greater customer involvement is incorporated into the product either to reduce costs or to provide grater convenience to the customer by, for instance, eliminating the need to wait for a salesperson.
2. How quickly will service be provided? Human queuing systems are an important aspect of product quality for services. The intended speed of service will affect staffing, job design, scheduling, and facility layout.
3. How standardized or customized will the service be? For example, freight rail service is usually highly standardized: trains are scheduled
to run between specific locations, and if customers want to ship or receive materials, they must be ready at those times.
4. What variety of services will be offered? If a fast-food restaurant will provide only carry-out service, there is no need for seating space in the facility or extra service personnel to clean the tables.
5. What geographical area will be served? American Express Corporation, which sells its products based on quick worldwide replacement of lost or stolen traveler’s checks and credit cards. This product characteristic requires a large international network of American Express offices and agents with a telecommunications system linking them.

Approaches to Improving Product and Service Designs

Approaches to Improving Product and Service Designs

Quality Function Deployment- “method to transform user demands into design quality, to deploy the functions forming quality, and to deploy methods for achieving the design quality into subsystems and component parts, and ultimately to specific elements of the manufacturing process.”

Computer-aided design- Computer-Aided Design (CAD) is the use of computer technology to aid in the design and particularly the drafting (technical drawing and engineering drawing)

Computer-added manufacturing-The process of using specialized computers to control, monitor, and adjust tools and machinery in manufacturing

Design for Manufacturability-It is the general engineering art of designing products in such a way that they are easy to manufacture. The basic idea exists in almost all engineering disciplines, but of course the details differ widely depending on the manufacturing technology.

Design for Maintainability-Design for Maintainability When human factors engineering is applied to minimize the time and effort required to perform preventive and unscheduled

Design for the Environment- It is a general concept that refers to a variety of design approaches that attempt to reduce the overall environmental impact of a product, process or service, where environmental impacts are considered across its life cycle

Target costing- Method used in the analysis of product design that involves estimating a target cost, via a desired profit and sales price, and then designing the product/service to meet that cost.

Product Design and Development Process

Product Design and Development Process
Process decisions must be made when:-
A new or substantially modified product or service is being offered
Quality must be improved
Competitive priorities have changed
Demand for a product or service is changing
Current performance is inadequate
The cost or availability of inputs has changed
Competitors are gaining by using a new process; or
New technologies are available

Process decisions directly affect the process itself, and indirectly the products and services that it provides. Let’s focus on the relevant common process decisions. In general, Operations managers must consider five common process decisions.
These are:
1. Process choice - Whether resources are organized around products or processes. It depends on volume and degree of customization to be provided
2. Vertical integration -Backward integration, and forward integration
3. Resource flexibility -ease with which employees and equipment can handle a wide variety of products, output levels, duties, and functions
4. Customer involvement
5. Capital intensity- mix of equipment and human skills in a process
A common classification of production process structures
We often classify processes based on their physical configuration, material and product flow, flexibility, and volume expectation.
There are five different process types, which a manager can choose, keeping in mind the relative importance of the following attributes:-
Quality,
Time,
Flexibility, and
Cost.
These are:
1. Project process
Selecting location for new plant
2. Job process
Machining precision metal tubes
3. Batch process
Producing a batchof textbooks
4. Line process
Auto assembly
5.Continuous process
Oil-refining process

Statistical Quality Control

Statistical Quality Control

It helps in verify that the business processes are indeed meeting the specifications. Under this we are using statistical methods and mathematical formulas to control over quality.

Tools of Statistical Quality Control
Process Capability
Upper Tolerance Limit
Lower Tolerance Limit
Six –sigma Quality
Control Chart
Acceptance Sampling
Taguchi’s Quality Loss Function
With the help of above tools we can compare the standards with actual results and take decisions to improve quality and increase profitability.