Integrating prospect theory with variable reference point into the conversion-based framework for linear ordinal...

Area of Science:

• Decision Sciences
• Operations Research
• Behavioral Economics

Background:

• Linear ordinal ranking (LOR) data is common but difficult to aggregate directly.
• Decision-makers' choices are often influenced by risk and psychological factors.
• Existing methods may not fully capture preferences or handle risk effectively.

Purpose of the Study:

• To propose a novel conversion-based method for aggregating LOR information under risk.
• To integrate prospect theory into the LOR aggregation process to model risk-sensitive decision-making.
• To enhance the computability and interpretability of LOR data.

Main Methods:

• Constructing information energy for LOR data.
• Analyzing the features of information energy to facilitate conversion.
• Integrating prospect theory with variable reference points into a conversion-based aggregation framework.
• Applying the method to a real-world example of financial product preferences.

Main Results:

• The proposed method successfully converts LOR information into interval utility values.
• The integration of prospect theory accurately reflects decision-maker behavior under risk.
• The example demonstrates the practicality, rationality, and stability of the method for LOR aggregation.

Conclusions:

• The conversion-based LOR aggregation method offers a robust approach for handling risk-sensitive preferences.
• This framework provides a more nuanced understanding of decision-making compared to traditional LOR aggregation.
• The method has practical implications for fields involving preference aggregation under uncertainty.