W17_YAW_Licensor Selection by Using Multi Attribute Decision


1.    Problem Definition.

In our company, we usually use passing grade method with simple weighting for licensor selection. However for our current licensor selection process, we decided to use multi attribute decision [1].

In this week blog posting, I will address this matter.

2.    Identify the Feasible Alternative.

The following table contains data of five licensors that will be selected.

Table 1 Licensor Data [2], [3]

W17_YAW_1

As shown in above table, there are four criteria of evaluation (in this case known as attribute).

Further, selection of licensor will use both methods of multi-attribute decision, namely non-compensatory model and compensatory model.

3.    Development of the Outcome for Alternative.

3.1.    Non-compensatory model.

Four non-compensatory models, that are (1) dominance, (2) satisficing, (3) disjunctive resolution, and (4) lexicography, will be used.

For evaluation of dominance, pairwise comparison between two alternatives will be done for all attributes, as shown in table 2.

Table 2 Evaluation of Dominance

W17_YAW_2

It is clear from above table that C is dominated by B, D and E, hence C will be eliminated.

The satisficing model is done by applying acceptable limit, as shown in Table 3, where there are no alternatives that are eliminated.

Table 3 Satisficing Model Evaluation

W17_YAW_3

Table 3 also is used to evaluate the disjunctive resolution, where concluded that all alternatives is acceptable because each has at least one attribute value that meets or exceeds the minimum expectation.

To conduct lexicography, the first should be done is to rank each attribute, as shown in table 4.

Table 4 Attributes Ranking

W17_YAW_4

And then Table 5 shows evaluation using lexicography, where “A” has highest rank attribute.

Table 5 Lexicography Evaluation

W17_YAW_5

3.2.     Compensatory model.

In this evaluation, two compensatory models, that are the non-dimensional scaling and the additive weighting technique will be used.

Ranking attribute by using non-dimensional scaling as shown in Table 6.

Table 6 Non-dimensional scaling

W17_YAW_6

After set relative rank for each attribute, further is to conduct additive weighting for all alternatives as shown in table 7.

Table 7 Additive weighting evaluation

W17_YAW_7

Note: Column Relative Rank is taken from Table 4.

As shown in Table 7, alternative “A” has highest rank.

4.   Selection of Criteria.

A selection criterion for licensor selection is the highest rank.

5.    Analysis and Comparison of the Alternative.

Table 8 shows ranking of licensors that resulted from both non-compensatory model and compensatory model.

Table 8 Ranking of licensors

W17_YAW_8

As shown in Table 8, it is interesting to see that both methods result the same rank order, where “A” has rank number I (highest) followed by D, B, E and C.

6.    Selection of the Preferred Alternative.

Off course, licensor A will be decided as winner in this licensor selection.

7.    Performance Monitoring and the Post Evaluation of Result.

Monitoring should be conducted during execution of the project to ensure that all requirements are met.

References:

  1. Sullivan, W.G., Wicks, E. M., Koelling, C. P. (2012). Engineering Economy, Chapter 14, page 551 to 569. Prentice Hall. Fifteenth Edition- Probabilistic Analysis – Decision Tree Analysis.
  2. Bidding Document. (2014). Licensor Selection. PT. ABCD. (Disguised).
  3. Licensors Proposal. (2014). Licensor Selection. PT. ABCD. (Disguised).

Advertisements

4 thoughts on “W17_YAW_Licensor Selection by Using Multi Attribute Decision

  1. AWESOME case study as usual Pak Yosep but your citations were weak at best…???

    How does decision tree analysis from Sullivan support this blog posting? Multi-attribute decision making no problem but decision trees?

    Also citing references which cannot be validated is not really a good practice……

    Nothing fatal here but not the usual high quality work you have been producing in previous weeks…

    What I would like to encourage you (and the rest of the team to start focusing on) are the AACE Recommended Practices. http://www.aacei.org/non/rps/welcome.asp

    THIS is the basis for where the questions on the AACE Exams are coming from , so now as we start to focus on preparing for the exams, those RP’s need to be getting more of your attention.

    BR,
    Dr. PDG, Boston MA

  2. Pingback: W3_MFO_ Gas Meter Selection by Using Multi Attribute Decision – EMERALD AACE 2017 – WEEKLY BLOG

  3. Pingback: W3_TH_ Gas Station Prime Mover Selection by Using Multi Attribute Decision – EMERALD AACE 2017 – WEEKLY BLOG

  4. Pingback: W2.1_MFO_Benchmarking Study of Estimation Process – EMERALD AACE 2017 – WEEKLY BLOG

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

w

Connecting to %s