Analytical Thinking & Decision Making: Iresearch Case Study Analysis

This document presents a detailed solution to the Iresearch case study, employing decision analysis techniques to address the company's decision-making challenges. The analysis includes the application of decision trees, calculation of expected values, and the rollback method to determine the most suitable approach for Iresearch. Specifically, the analysis focuses on three key decisions: proposal development, platform selection, and software package selection. The expected values are calculated for different software options (A, B, C, and D) across web and mobile platforms, considering development costs, platform costs, and proposal costs. The profit calculations reveal that mobile software C and web-based software B offer the best potential returns. The document concludes with recommendations for the managers, based on the quantitative analysis and a review of relevant literature on decision-making methodologies. Desklib provides students with access to this and many other solved assignments.

Design Thinking Assignment
Iresearch Case Study
Name of the Student:
Student ID:
Name of the University:
Author’s note:

3. Decision Analysis and Decision Tree
The decision analysis for the project of Iresearch would be done considering the limitation of the
works and the alignment of the successful implication model. The decision involves whether the
proposal for the ACME client would be made or not. The decisive method of analyzing the
minute factors in favor or against the development of the proposal. According to our study there
are three major decisions required to be executed for ensuring the work completion and the
decision to be made. The three main steps for the Iresearch are Decision Proposal, Selection of
Right Platform, and Selection of Software Package. These have been explained below,
Decision Proposal: The Iresearch require the implication of the effective proposal
documentation for aligning the works and integrating the smart analysis. The decision proposal
would be made for ensuring that before taking the proposal all required and crucial information
are collected.
Selection of Right Platform: The right platform for the development of the platform by the
Iresearch would be another crucial factors for integrating and executing the works. The right
platform selection would be eased with the alignment of the factors for development.
Selection of Software Package: The selection of the right platform is very helpful for ensuring
the analysis of the works and formation of the effective work development. The right package
would be selected for ensuring that proper and effective work can be executed.

4. Expected Values and Rollback Method of the Decision Tree
We would consider the web and mobile applications for all four software A, B, C, and D. The
software A, B, C, and D have respectively 1, 1, 0.65, 0.45, 0.75, 0.75, 0.45, and 0.65 success
ratings. Hence the profit calculation would be done for calculating the cost output, investment,
and profit calculation. The software A, B, C, D has success profit rating of £321,000.00,
£326,000.00, £425,900.00, £450,950.00, £398,000.00, £401,750.00, and £443,300.00. Now if
success probability is multiplied respectively we get, £321,000.00, £326,000.00, £276,835.00,
£202,927.50, £298,500.00, £301,312.50, and £199,485.00.
The expected values of the project cost are given below,
Softw
are
Platfo
rm
Development
Cost
Platform
Cost
Proposal
Cost Probability Cost Output
Succ
ess
Fail
ure Success Failure
A
WEB £145,000.00 £24,000.0
0
£10,000.0
0 1 0 £179,00
0.00 £0.00
Mobil
e £145,000.00 £19,000.0
0
£10,000.0
0 1 0 £174,00
0.00 £0.00
B
WEB £80,000.00 £24,000.0
0
£10,000.0
0 0.65 0.35 £74,100.
00
£39,90
0.00
Mobil
e £80,000.00 £19,000.0
0
£10,000.0
0 0.45 0.55 £49,050.
00
£59,95
0.00
C
WEB £102,000.00 £24,000.0
0
£10,000.0
0 0.75 0.25 £102,00
0.00
£34,00
0.00
Mobil
e £102,000.00 £19,000.0
0
£10,000.0
0 0.75 0.25 £98,250.
00
£32,75
0.00
D
WEB £92,000.00 £24,000.0
0
£10,000.0
0 0.45 0.55 £56,700.
00
£69,30
0.00
Mobil
e £92,000.00 £19,000.0
0
£10,000.0
0 0.65 0.35 £78,650.
00
£42,35
0.00
The profit calculation for the options is given below,
Software Platform Investment Profit Profit*Probability

Calculation
A WEB £500,000.0
0 £321,000.00 £321,000.00
A Mobile £500,000.0
0 £326,000.00 £326,000.00
B WEB £500,000.0
0 £425,900.00 £276,835.00
B Mobile £500,000.0
0 £450,950.00 £202,927.50
C WEB £500,000.0
0 £398,000.00 £298,500.00
C Mobile £500,000.0
0 £401,750.00 £301,312.50
D WEB £500,000.0
0 £443,300.00 £199,485.00
D Mobile £500,000.0
0 £421,350.00 £273,877.50
Hence, it is evident that mobile software C and web based software B would bring about the best
profit returns.

Bibliography
Aich, S., Younga, K., Hui, K.L., Al-Absi, A.A. and Sain, M., 2018, February. A nonlinear
decision tree based classification approach to predict the Parkinson's disease using different
feature sets of voice data. In Advanced Communication Technology (ICACT), 2018 20th
International Conference on(pp. 638-642). IEEE.
Frosst, N. and Hinton, G., 2017. Distilling a neural network into a soft decision tree. arXiv
preprint arXiv:1711.09784.
Goodman, K.E., Lessler, J., Cosgrove, S.E., Harris, A.D., Lautenbach, E., Han, J.H., Milstone,
A.M., Massey, C.J. and Tamma, P.D., 2016. A clinical decision tree to predict whether a
bacteremic patient is infected with an extended-spectrum β-lactamase–producing
organism. Clinical Infectious Diseases, 63(7), pp.896-903.
Hong, H., Pradhan, B., Xu, C. and Bui, D.T., 2015. Spatial prediction of landslide hazard at the
Yihuang area (China) using two-class kernel logistic regression, alternating decision tree and
support vector machines. Catena, 133, pp.266-281.
Quist, J., Mirza, H., Cheang, M.C.U., Telli, M.L., Lord, C.J., Tutt, A.N.J. and Grigoriadis, A.,
2017. Association of a four-gene decision tree signature with response to platinum-based
chemotherapy in patients with triple negative breast cancer.
Zhang, Y., Wang, S., Phillips, P. and Ji, G., 2014. Binary PSO with mutation operator for feature
selection using decision tree applied to spam detection. Knowledge-Based Systems, 64, pp.22-31.