Vous êtes sur la page 1sur 38

Application of the Analytic Hierarchy Process (AHP) for Selection of Forecasting Software

Saptarshi Roy Chowdhury(11DCP041) Tarun Gautam(11DCP100) Joseph Thomas(11DCP076) Adil Anwar(11DCP003)

Introduction AHP Forecasting


-- A Forecasting tool used by many companies. AHP

tool along with other decision making systems help the companies to analyze the factors on which the companies can decide the areas they can look up to. And also the factors on which they have to improve upon.

Introduction
Outline:
History Of AHP AHP introduction AHP criterions Deciding Factors. Case Study on Software

-Deciding on the Criteria


AHP using Expert Choice software

-Sensitivity Analysis -Our Case Study

The Analytic Hierarchy Process (AHP)


AHP Model
Problem is structured as a hierarchy Reflects the decision problems major components (decision criteria) and their inter-connections (comparisons with each other) In our problem, we have a single-level hierarchy of decision criteria

The Analytic Hierarchy Process (AHP)


Comparisons
A judgment or comparison is the numerical representation of a relationship between two elements that share a common parent (Saaty, 1994) The judgments made in a scale ranging from 1 to 9

The Analytic Hierarchy Process (AHP)


Given values (1-9) 1 Equal 3 Moderate Explanation Both alternatives have equal importance. One of the alternatives is slightly more important than the other. One of the alternatives is judged as strongly more important than the other by experts. One of the alternatives is judged as very strongly important compared to the other. One alternative is strictly superior to the other one. Used for compromised judgments when necessary.

5 Strong

7 Very Strong

9 Extreme Importance 2, 4, 6, 8 Intermediate values

The Analytic Hierarchy Process (AHP)


Consistency
One makes redundant comparisons to improve the validity of the answer. Redundancy gives rise to multiple comparisons of an element with other elements and hence to numerical inconsistencies. (Saaty, 1994) Inconsistency is tolerable if does not exceed 10%.
7

The Analytic Hierarchy Process (AHP)


AHP is distinguishable from its alternatives
Even though constructing an AHP model requires eliciting of extensive data from a group of respondents, and is thus time consuming in this respect, it is fairly insensitive to judgmental errors. (Karlsson, 1998)

Some Questions which AHP gives Solution :-

.How does the rm perform in terms of service quality in relation to competitors? . Given the rms resources, which service initiatives will enhance its service competitiveness? .Which service areas require immediate improvement? How should the rms service improvement be prioritized? .What opportunities exist for service improvement in relation to the competition

Some Other Decision making Soft -wares other than AHP


Customer service audits (Takeuchi and Quelch, 1983) Gap analysis(Zeithaml, 1988) SERVQUAL(1988) SERVPERF(1994) Critical incident Technique(Bitner, 1990)
10

History Of AHP
In the late 1960s, Thomas Saaty, one of the pioneers of Operations Research, and author of the first Mathematical Methods of Operations Research textbook and the first queuing textbook, was directing research projects for the Arms Control and Disarmament Agency at the U.S. Department of State. It was basically the start of AHP process he discovered while controlling the budget. Years later, Saaty was motivated to attempt to develop a simple way to help ordinary people make complex decisions. The result was the Analytic Hierarchy Process a synthesis of existing concepts that attests to Saatys genius through its power and simplicity.
11

Three Primary AHP functions : Structuring Complexity Measurement on a Ratio Scale Synthesis

12

Principles & Axioms of AHP


There are Three Related basic components Of AHP. Decomposition comparative judgments hierarchic composition or synthesis of priorities

13

Decomposition
The decomposition principle is applied to structure a complex problem into a hierarchy of clusters, sub clusters, sub-sub clusters and so on.

Comparative Judgments
The principle of comparative judgments is applied to construct pairwise comparisons of all combinations of elements in a cluster with respect to the parent of the cluster. These pairwise comparisons are used to derive 'local priorities of the elements in a cluster with respect 14 to their parent.

Synthesis
hierarchic composition or synthesis is applied to multiply the local priorities of the elements in a cluster by the 'global' priority of the parent element, producing global priorities throughout the hierarchy and then adding the global priorities for the lowest level elements.
15

Case Study on selecting Forecasting Soft wares using AHP


Soft wares which are taken into account :NCSS MINITAB Decision Pro Forecasting Tool Aura Systat
16

Research Methodology
We have taken 50 users who have used all these soft-wares. Over a three-week period, the questionnaire was administered to customers who were accustomed to use these soft wares. about one in four customers who were approached was willing to ll in the questionnaire. Johns and Tyas (1996) also encountered the problem of respondents not being willing to participate in a survey. In the present study, each respondent was given a dollar for participating in the survey. The respondents were rst screened to ensure that they had patronised all checking for inconsistencies giving a response rate of 84 per cent.
17

Deciding on the Criteria


We identified seven criteria
Six of these criteria derived from Tashman and Hoover (2001)
Data preparation Method selection Method implementation Method evaluation Assessment of uncertainty Forecast presentation

The seventh criterion: Ease of use


Selected as the most important feature by managers (selected by ~86% of them) (Sanders and Manrodt, 2003) 18

Deciding on the Criteria


Some criteria that were not included:
Price Country of Origin Import/Export capabilities

19

Software Selection & Weight Defamation :We have here selected the Soft-wares & defined the weightage accordingly.
Goal: Software Selection

Data Preparation ( 0.112 )

Method Selection ( 0.273 )

Method Implementation ( 0.176 )

Method Evaluation ( 0.054 )

Assessment of Uncertainity ( 0.044 )

Forecast Presentation ( 0.089 )

Ease of Use ( 0.250 )

20

Application of the AHP using Expert Choice


Comparing the criteria with each other:

Comparing each software according to each criteria (7 matrices) Entering these matrices as input to Expert Choice
21

Our Findings and Insights


The Priorities Computed by Expert Choice Software and the Values of Criteria Excluded from the AHP Model
Software Name NCSS DecisionPro Minitab Forecasting Tool * Aura Systat Priority 0.255 0.232 0.197 0.129 0.099 0.088 Price Country of Origin $600 $795 $1195 $75 $441 $1299 USA USA USA USA Russia USA
22

16000 14000 12000 10000 8000 6000 4000 2000 0 1 6 11 16 21 26 31 36 41 46 51 56 61 66 71 76 81 86 91 96

Exhibits Trend and Strong Seasonality

23

Our Findings and Insights

24

Our Findings and Insights


DecisionPro software, the best with respect to Method selection NCSS ranks as the top software product NCSS is shows superiority with respect to Forecast precision criterion, with the Aura software Forecasting Tools software
The lowest-price alternative Highest score with respect to the Ease of use Worse with respect to other criteria

Minitab software advantageous with respect to Uncertainty assessment Aura, in Russia


25

Sensitivity Analysis

26

Sensitivity Analysis

27

Case Study on Mobile companies


A Survey was done to analyze the factors which international customers take into account before buying a mobile phone. We have compared certain features with the help of AHP. We have also tried to define the factors on which a firm can improve or emphasize in their product line.
28

Features taken into account


Brand Style Camera Quality User friendliness Applications Price Battery Durability Durability
29

Research Methodology
Questionnaire Design :In accordance with the conceptual framework described above, the questionnaire was structured into two sections. The rst section contained twenty eight pairwise comparison items for customer evaluation of the importance of service dimensions in mobile companies.
30

Research Methodology Contd.


The rst level the service-dimension level addressed the relative importance of various service dimensions in dening service quality. Customers were asked to compare pairs of service dimensions (for example, Brand versus Style) and to indicate whether they felt that one dimension was equal to, more important than or less important than another dimension. The second level of the hierarchy the choice level compared the performance of service providers (in this case, mobiles) with respect to the service dimensions. The customers were asked to state their preference for the mobiles in a pairwise manner on a nine-point relative measurement Scale.
31

Related Literature
Tashman and Hoover (2001)
General insights and suggestions Ratings of the software products and the categories Omitted criteria such as ease of learning, and easy of use by decision makers who possess only a modest statistical background

Our study takes as audience the decision maker


With less technical knowledge Who has limited time to test various software.

32

Related Literature
Application of the AHP to selection of software:
Ossadnik and Lange (1999): Evaluate three AHP software products through an AHP-based study Lai et al. (2002): A case study that six software engineers participated, which involved selection of a multi-media authorizing system
Post-study survey revealed that the AHP was more preferable than Delphi as a group-decision making method.

Jung and Choi (1999) use AHP to derive weights of software modules based on access frequencies of the modules- that are then used in optimization models.
33

Questionnaire Design
Over a three-week period, the questionnaire was administered, About 100 students were questioned. about three in five customers who were approached was willing to ll in the questionnaire. Johns and Tyas (1996) also encountered the problem of respondents not being willing to participate in a survey. A total of 80 customers participated in the survey. After checking for inconsistencies (see Data analysis, below) ten respondents were excluded giving a response rate of 90 per cent.
34

Data Analysis
Each respondents weights and scores were computed using Microsoft EXCEL. Then all respondents weights and satisfaction scores were analysed using SPSS. Applying the AHP methodology to service quality involved ve steps referred to here as analytic hierarchy process for service quality (AHP-SQ). The AHP-SQ steps were as follows:35

Data Analysis Contd.


Step 1. Obtain customers trade off judgments for the service dimension and mobile choice displayed in the pairwise comparison matrices. Step 2. Check for consistency. Step 3. Compute the weights of the service dimensions and satisfaction scores for the restaurant choice of each respondent. (4) Step 4. Compute the mean overall weights and satisfaction scores over all respondents. 36 (5) Step 5. Compute the quality gap.

Conclusion
Introduced the use of the AHP to the forecasting literature for the first time, to our knowledge. Insights with respect to which software products would be most appropriate for which types of companies Sensitivity analysis show that the weights given to decision criteria can change the priorities and rankings of the software products.
37

Questions?

38

Vous aimerez peut-être aussi