Empirical Analysis of Decision Recommendation Models for Various Processes from A Pragmatic Perspective

Abstract

Decision recommendation models allow researchers and process designers to identify & implement high-efficiency processes under ambiguous situations. These models perform multiparametric analysis on the given process sets in order to recommend high quality decisions that assist in improving process-based efficiency levels. A wide variety of models are proposed by researchers for implementation of such recommenders, and each of them varies in terms of their functional nuances, applicative advantages, internal operating characteristics, contextual limitations, and deployment-specific future scopes. Thus, it is difficult for researchers and process designers to identify optimal models for their functionality-specific use cases. Due to which, they tend to validate multiple process models, which increases deployment time, cost & complexity levels.To overcome this ambiguity, a detailed survey of different decision process recommendation models is discussed in this text. It was observed that Fuzzy Logic, Analytical Hierarchical Processing (AHP), Technique for Order Performance by Similarity to Ideal Solution (TOPSIS), and their variants are highly useful for recommendation of efficient decisions. Based on this survey, readers will be able to identify recently proposed decision recommendation models, and identify functionality-specific models for their deployments. To further assist the model selection process, this text compares the reviewed models in terms of their computational complexity, efficiency of recommendation, delay needed for recommendation, scalability and contextual accuracy levels. Based on this comparison, readers will be able to identify performance-specific models for their deployments. This text also proposes evaluation of a novel Decision Recommendation Rank Metric (DRRM), which combines these parameters, in order to identify models that can optimally perform w.r.t. multiple process metrics. Referring to this parameter comparison, readers will be able to identify optimal recommendation models for enhancing performance of their decision recommendations under real-time scenarios.