International Journal of Applied Engineering Research ISSN 0973-4562 Volume 12, Number 19 (2017) pp. 9067-9073
© Research India Publications. http://www.ripublication.com
9067
Decision Making Modelling with Logistic Regression Approach
Kataresada Ketaren
1
and Novdin M. Sianturi
2
1,2
Civil Engineering, University of Simalungun, P. Siantar, Indonesia Kopertis Area 1 Medan, Indonesia.
Abstract
Decision making is a process of making choices by
identifying decision, gathering information, identifying
alternatives, and also assesing alternative resolutions. The
decision making which is discussed in this study is related to
bid/ no bid. In an effort to uncover the main factors that
characterize the one distinct of bidding decisions, namely bid/
no bid, this study identifies the key determining factors and
their importance weights. Significant factors in the decision to
bid process are identified and a pro-forma to elicit a numerical
assessment of these factors is developed and validated using
the bid/ no bid decision-makers from a construction company.
Using the pro-forma, data were collected from the
collaborating company for historical bid opportunities. The
aim of this research paper is to analyse and present factors
which has a positive and significant relationship the decision
to bid/ no bid. Statistical techniques are used to get a better
understanding of data characteristics and to have the model
process. Factor analysis was used in this research to find a
way to summarize the information contained in a number of a
original variables into a smaller set of new, composite
dimensions or factor with a minimum loss of information.
Logistic regression models were developed with the factors as
independent variable from previous factor analysis process to
get the final model with predictive accuracy rate of 87
percent. The positive and significant factors contributing to
the prediction were competition in the market, market share,
and experience, demonstrate that the model functions
effectively in predicting the bid/ no bid decision process.
Keywords: Bid/no bid decision, contractor, strategic decision,
decision making, factor analysis, logistic regression
INTRODUCTION
The bidding process involves two crucial decisions: first,
whether bid or not to bid for a project and second, the
determination of the bid price. The bid/no bid decision is
complex and dynamic, involving many factors also while the
selection process of the most appropriate projects for which to
bid or not to bid is fundamental decision to a successful
commercial strategy (Shash, 1993)[16]. Bid/ no bid decision-
making is a critical activity for a contractor. Limited by both
the nature of and the competition for bid opportunities, bid/ no
bid decision is associated with uncertainty and complexity
(Lin and Chen, 2004)[11]. One of the most important
decisions that have to be made by contractor firms is whether
to bid or not to bid for a project, when an invitation has been
received. Because of the importance of his decision making
issue, the decision is not considering only about a probability
to win the tender but also taking into account of the latter part,
which is being able to finish the job as planned with the
expected profit (Lin and Chen, 2004)[11]. Since contractors’
bidding behaviors are affected by numerous factors related
both to the specific features of the project and dynamically
changed situations, bidding decision problems are highly
unstructured. The usual practice is to make bid decisions on
the basis of intuition derived from a mixture of gut feelings,
experience and guesses (Drew, 2001)[6]. However, the
development of successful bidding strategies is a key factor to
the survival of a contracting company. The basis of a
successful strategy is to filter out losing bid opportunities and
concentrate proposal efforts on bid opportunities that, when
successful, assist in satisfying the objectives of the
organization. With regard to preventing an organization from
dissipating its energies in preparing a losing proposal,
Rosenau, (1998)[15] even asserted that the bid/no-bid
decisionmust be made within the context of the organization’s
strategic framework. Numerous researchers have developed
models for bid/no bid and mark-up size decisions.
Previous Decision to Bid/No Bid Decision Models
Ahmad (1990)[1] presents a deterministic worth evaluation
model of the bid/no-bid decision problem. A suggested
decision is made by comparing this score with a desired
minimum (threshold) score. Although the model is illustrated
using ahypothetical bidding decision-making scenario, the
model is theoretical, based on a set of attributes obtained from
a questionnaire survey of 400 US general contractors.
Thirteen attributes (factors) lower-level criteria, representing
major objectives of a construction firm, are divided into four
hierarchical groups: job-related, market-related, firm-related
and resource-related. A great volume of literature concerned
with bidding strategies has resulted in many bidding models.
However, Friedman’s study was the first research aimed to
develop a quantitative bidding optimization model. Sadly, the
evidence suggests that practitioners have made relatively little
use of those models (Rothkopf and Harstad, 1994)[18] and
most of these models continued in academic circles and did