Chapter: 6 : Decision Making• Decision Making Concepts:• The word ‘decision’ is derived from the Latin root decido, meaning to cut off. • The concept of decision, therefore, is settlement, a fixed intention bringing to a conclusive result, a judgment, and a resolution.• A decision is the choice out of several options made by the decision maker to achieve some objective in a given situation.

• The major characteristics of the business decision making are:1. Sequential in nature : In business, the decisions are

not isolated events. Each of them has a relation to some other decision or situation.

2. Exceedingly complex due to risks and trade offs: The decision making process is a complex process. The complexity is the result of many factors, such as inter-relationship among the experts or decision makers, a job responsibility, a question of feasibility, the codes of morals and ethics, and a probable impact on business.

3. Influenced by personal values: The personal values

of the decision maker play a major role in decision making. The culture, the discipline and the individual’s commitment to goals will decide the process and success of the decision.

4. Made in institutional settings and business environment : The decision making process requires creativity, imagination and a deep understanding of human behavior. The process covers number of tangible and intangible factors affecting the decision process.

• Rational Decision-making:• A rational decision is the one which effectively and efficiently, ensures the achievement of the goal for which the decision is made.• If it is raining, it is rational to look for a cover so that you do not get wet.• If you are in business and want to make profit, then you must produce goods and sell them at a price higher than cost of production• So there is no right or wrong decision, but a rational or an irrational decision.

• The rationality of the decision made is not the same in every situation. It will vary with the organization.• Simon Herbert A differentiates among the types of rationality.• A decision, in a given situation is:• Objectively rational if it maximizes the value of the objective.• Subjectively rational if it maximizes the attainment of value within limitation of the knowledge and awareness of the subject.• Consciously rational to the extent the process of the decision-making is deliberate and a conscious one.• Organizationally rational to the degree of the orientation towards the organization.

• Personally rational to the extent it achieves an individuals personal goals.• Gross Bertram M suggests three dimensions of rationality :1. The degree of satisfaction of human interest.2. The degree of feasibility in achieving the

objectives.3. A consistency in decision-making.

• The problems in Making Rational Decisions:1. Ascertaining the problem : As Peter Drucker points

out, “ the most common source of mistakes in the management decisions is the emphasis on finding the right answers rather than the right questions”.

2. Insufficient knowledge : Complete knowledge is necessary.

3. Not enough time to be rational : The decision maker is under pressure to make decisions.

4. The environment may not cooperate: Sometimes, the timing of the decisions is such that one is forced to make a decision but the environment is not helpful for it. And the decision may fail.

5. Other limitations : are the need for a compromise among the different positions, misjudging the motives and values of people, poor communications, misappraisal of uncertainties and risks, and inability to handle the available knowledge and human behavior.

• Decision-Making Process:• Decision-making is a process which the decision

maker uses to arrive at a decision. The core of this process is described by Herbert Simon in a model.

• There are three phases in this model.1. Intelligence: Raw data collected, processed and

examined. Identifies a problem calling for a decision.2. Design: Inventing, developing and analyzing the

different decision alternatives and testing the feasibility of implementation. Assess the value of the decision outcome.

3. Choice: Select one alternative as a decision, based on the selection criteria.

• In the intelligence phase, the MIS collects the data. The data is scanned, examined, checked and edited. Further, the data is sorted and merged with other data and computations are made, summarized and presented. It highlight the significant differences between the actual and the expected, the budgeted or the targeted.

• In the design phase, the manager develops a model of the problem situation on which he can generate and test the different decisions to facilitate its implementation. If the model developed in useful in generating the decision alternatives, he then further moves into phase of selection called as choice.

• In the phase of choice, the manager evolves a selection criterion such as maximum profit, least cost, minimum waste, least time taken, and highest utility. The criterion is applied to the various decision alternatives and the one which satisfies the most is selected.

• In these three phases, if the manager fails to reach a decision, he starts the process all over again from the intelligence phase where additional data and information is collected, the decision-making model is refined, the selection criteria is changed and decision is arrived at.

• Decision Making System : Types• There are two types of systems based on the managers knowledge about the environment:• Closed decision making system• Open decision making system• If the manager operate in a known environment then it is a closed decision making system.

• The condition of the closed decision making system are:1. The manager has a known set of decision

alternatives and knows their outcomes fully in terms of value, if implemented.

2. The manager has a model, a method or a rule whereby the decision alternatives can be generated, tested, and ranked for selection.

3. The manager can choose one of them, based on some goal or objective criterian.

• If the manager operated in an environment not known to him, then the decision-making system is termed as an open decision making system.• The condition of this system is:1. The manager does not know all the decision

alternatives.2. The outcome of the decision is also not known fully. The

knowledge of the outcome may be a probabilistic one.3. No method , rule or model is available to study and

finalize one decision among the set of decision alternatives.

4. It is difficult to decide an objective or a goal and therefore, the manager resorts to that decision, where his aspirations or desires are met best.

• Types of Decisions:• The types of decisions are based on the degree of knowledge about the outcomes or the events yet to take place.• If the manager has full and precise knowledge of the event or outcome which is to occur, then the decision making is not a problem. If the manager has full knowledge, then it is a situation of certainty.• If he has partial knowledge or a probabilistic knowledge, then it is decision-making under risk.• If the manager does not have any knowledge at all, then it is decision-making under uncertainty.

• A good MIS tries to convert a decision-making situation under uncertainty to the situation under risk and further to certainty.• Decision-making in the operations management , is a situation of certainty. This is mainly because the manager in this field, has fairly good knowledge about the events which are to take place, has full knowledge of environment, and has a predetermined decision alternatives for choice or for selection.• Decision-making at the middle management level is of the risk type. • At the top management level, it is a situation of total uncertainty on account of insufficient knowledge of the external environment and the difficulty in forecasting business growth on a long-term basis

• Nature of Decisions: • Decision making is a complex situation. To resolve the complexity, the decisions are classified as programmed and non-programmed decisions.• If a decision can be based on a rule, method or even guidelines, it is called the programmed decision. If the stock level of an item is 200 numbers, then the decision to raise a purchase requisition for 400 numbers, is a programmed-decision-making situation.• The decision maker here is told to make a decision based on the instructions or on the rule of ordering a quantity of 400 items when its stock level reaches 200.

• Since the programmed decisions are made through MIS, the effectiveness of the rule can be analyzed and the rule can be reviewed and modified from time to time for an improvement.• The programmed decision-making can be delegated to a lower level in the management cadre.• A decision which cannot be made by using a rule or a model is the non-programmed decision. Such decisions are infrequent but the stakes are usually larger.• The MIS in the non-programmed-decision situation, can help to some extent, in identifying the problem, giving the relevant information to handle the specific decision making situation.

• The Law of Requisite Variety :• The requisite variety of situations means that for efficient programmed decision-making, it is necessary for the manager to provide:a. All the decision alternatives and the choices in

each probable state.b. The decision rules to handle the situationc. The system or the method to generate a decision

choice.• In a closed decision making situation, the

programmed decision making system works efficiently, while in the open decision making situation, it is not efficient.

• Methods for Deciding Decision Alternatives:• There are several methods which help to the manager to decide among alternatives:1. Optimization Techniques2. Payoff Analysis3. Decision Tree Analysis• All the operational research models use

optimization techniques, to decide on the decision alternatives.

• When a decision making situation can be expressed, in terms of decision versus the probable event, and its pay-off value, then it is possible to construct a matrix of the decision versus the events described by a value for each combination. •The method of decision tree can be adopted, if the decision-making situation can be described as a chain of decisions.• The process of decision-making is sequential and a chain of decisions achieves the end objective.• The use of both the pay-off matrix and the decision tree requires a probabilistic knowledge of the occurrence of events.

• Optimization Techniques:• Linear Programming, Integer Programming, Dynamic Programming, Queuing Models, Inventory Models, Capital Budgeting Models and so on are the examples of optimization techniques.• These methods are used in cases where decision-making situation is closed, deterministic and requires to optimize the use of resources under conditions of constraints.• To handle these situations, software packages are available. These methods are termed operational research techniques.

• The Payoff analysis:• When all the alternatives and their outcomes are not known with certainty, the decision is made with the help of payoff analysis.• The payoff matrix is constructed where the rows show the alternatives and the columns show the conditions or the states of nature with the probability of occurrence.• The intersection of column and row shows the vaue of an outcome resulting out of the alternative and the state of the nature.• Which is shown in figure.

Payoff Matrix IYour Decision Alternatives

Competitor’s Decision: Probability

No Change

0.50

Increase

0.20

Decrease

0.30

Expected gain

No change in the price

Increase in Price

Decrease the price

4

6

10

5

4

12

8

3

4

5.40

4.70

8.60

• The concept of utility relates to the money value considered by the decision maker.• Utility is measured in terms of utile. Money has a value of a different degree to different decision makers depending upon the amount, and also the manner in which it is received.• If rupee 1 is equal to 1 utile, then Rs 100 million is not 100 million utile but could be much more.• The utile value will be different if the money is received in one lot as against in parts in several years.• The utility function is different for different decision makers.

• In our example of pricing, if we replace the values by utile, the matrix would be as given below in table.

Decision Competitor’s choice: Probability

No change

0.50

Increase

0.20

Decrease

0.30

Expected Utility

No change in the price

Increase the price

Decrease the price

4

200

100

50

4

20

200

400

4

72.00

220.80

54.12

Payoff Matrix II

• Decision tree analysis:• When a decision maker must make a sequence of decisions, the decision tree analysis is useful in selecting the set of the decisions.• The method of analysis can be explained by an example. • The decision tree is drawn in fig with the help of symbols.

• Let us take an example of investment in production capacity for a planning period of five years.• In this decision situation there are two decision points and six paths as given below. • The path which gives maximum cash flow is the right decision path. The cash flow values are as under:

Path Expected.cashflow

ABG ---- CollaborationABD ---- No CollaborationACEH ---- Collaboration Ist phase, Collaboration IInd Phase

ACEI ---- Collaboration Ist phase, No Collaboration Iind PhaseACFJ ---- No Collaboration Ist phase Collaboration IInd phaseACFK ---- No Collaboration Ist phase No collaboration Iind phase

7.97.59.2

8.0

8.2

7.4

• The problem is whether to expand now with a large capacity or to invest now in small capacity and make a decision of expansion after one year with the help of a collaboration or without a collaboration under certain demand conditions.• Since the highest expected cash flow path is ACEH, the decision is to invest in a small capacity in the Ist phase and invest in the remaining capacity in the second phase with the assistance of the collaboration.• The decision tree approach is useful when you visualize a series of decisions having alternative paths with the associated probabilities and the cash flows for each path for more than one year.

• Decision Analysis by Analytical Modeling:• The process is executed through analytical modeling of problem and solution.• The model is analyzed in four ways:1. What if analysis2. Goal Seeking Analysis3. Sensitivity Analysis4. Goal Achieving Analysis

• What If Analysis: Decisions are made using a model of the problem for developing various solution alternatives and testing them for best choice. The model is built with some variables and relationship between variables. • The considered values of variables or relationship in the model may not hold good and therefore solution needs to be tested for an outcome, if the considered values of variables or relationship change. This method of analysis is called ‘What if analysis’.• For example in decision-making problem about determining inventory control parameters lead time is assumed fairly constant and stable for a planning period.

• Based on this, the inventory parameters, are calculated. Inventory manger wants to know how the cost of holding inventory will be affected if lead time is reduced by one week or increased by one week.• The model with changed lead time would compute the cost of holding inventory under new conditions.• Such type of analysis can be done for purchase price change, demand forecast variations and so on. • Such analysis helps a manager to take a more learned decisions. • What if analysis creates confidence in decision-making model by painting a picture of outcomes under different conditions.

• Sensitivity Analysis: In What if analysis you test the effect on solution by changing the value of number of variables simultaneously or changing the relations between them. • But in sensitivity analysis, a special case of what if analysis, only one variable is changed and rest are kept unchanged.• In the problem of inventory, sensitivity analysis can be used to assess the cost of holding inventory, if cost of item increases by 20 per cent in sensitivity analysis, you are testing how sensitive is the cost of holding inventory to the change in cost of item.• Sensitive analysis helps to understand the significance of variable in decision-making and improves the quality of decision-making.

• Goal Achieving Analysis: In goal seeking analysis, you analyze the problem in exactly reverse way as that of what if analysis or sensitivity analysis. • In goal seeking analysis, goal is fixed and you go down to analyze the variables and values, which would help to seek that goal.• For example in our inventory problem you would fix a goal of achieving the cost of holding inventory of an item at the level of Rs. 10,00,000.• Goal seeking analysis will help you to arrive at values of parameters to attain the inventory level of Rs. 10,00,000.

• Goal Seeking Analysis: In goal seeking analysis, you do not fix the goal but you try to achieve a goal of an optimum value arrived at after satisfying all the constraints operating in the problem.• In Optimization analysis, you come to know which are critical constraints and which are limiting the value of goal.• The decision maker can use this analysis to work on constraints and resources and find ways to improve upon solution to seek highest goal.

• Behavioral Concepts in Decision-Making:• A manager, being a human being, behaves in a peculiar way in a given situation. The response of one manager may not be the same as that of the two other managers, as they differ on the behavioral platform. • Even though tools, methods and procedures are evolved, the decision is many a times influenced by personal factors such as behaviour.