A scenario-based approach for investment prioritization using robustness analysis and uncertain data

For any economic entity (investor) facing financial constraints, selecting the most optimal investment project is of paramount importance. Given the significance of the time value of money and the critical role of the Net Present Value (NPV) method in evaluating project profitability, traditional investment appraisal techniques often fail to comprehensively account for uncertainties, ambiguities, and future fluctuations. In this regard, the present study aims to enhance the investment project prioritization process.

This research integrates the NPV model with robustness analysis using uncertain data. The proposed approach comprises eight stages: 1) Identifying decision alternatives, 2) Estimating uncertain investment costs, 3) Estimating uncertain project revenues, 4) Defining alternative future scenarios, 5) Normalizing and converting data into deterministic values, 6) Computing the NPV index under different scenarios, 7) Assessing the robustness of projects, and 8) Ranking the alternatives.

The proposed approach was implemented in a case study involving the selection of an optimal investment project among restaurant, café, eco-lodge, water recreation, juice bar, traditional eatery, and fast-food business options in Tonekabon County. Considering uncertainty, the unpredictability of future conditions, and decision-makers’ hesitations in data estimation, the traditional eatery project was identified as the most suitable investment, whereas the water recreation project was deemed the least favorable. This study demonstrated that employing uncertain data yields superior performance compared to optimistic, pessimistic, and most-likely estimations.

Originality/Value:

 Compared to previous studies, the proposed approach enhances the accuracy and rationality of investment evaluations by incorporating uncertain data. This methodology aids decision-makers in making more informed choices when confronted with complex and uncertain conditions. Additionally, the new approach eliminates the imposition of additional constraints on decision-makers/owners in estimating problem-related data.