Stock Market Prediction Based Multi-Attribute Decision Making Model Using Picture Fuzzy ˆZ-Information

Abstract In the ever-evolving finance field, accurate market forecasts are necessary for traders and investors. Utilizing machine learning and data analysis, our focus is on developing an advanced model to predict stock prices with accuracy by analyzing historical trends. This research paper tackles pressing issues in Stock Market Prediction through the utilization of the multi-criteria group decision-making (MGCDM) approach. The approach offers a systematic means to assess and contrast various criteria and choices, enhancing decision-making accuracy. To further enhance this methodology, we integrate Zadeh’sˆZZadeh’sˆ Zadeh’sˆZ-numbers with constraints and reliability measures to address existing gaps in understanding their full capabilities. Our exploration focuses on utilizingˆZutilizingˆ utilizingˆZ-numbers, characterized by unpredictability and fuzziness, by merging them with picture fuzzy sets (PFSs) to capitalize on their potential benefits. To improve the capacity to handle completely unclear decisions and efficiently capture the fuzzy character, versatility, and application of decision-making data, we created picture fuzzyˆZfuzzyˆ fuzzyˆZ-numbers for pairwise comparisons of decision-makers possibilities. We created weighted averaging, ordered weighted averaging, hybrid averaging, weighted geometric, ordered weighted geometric , and hybrid geometric operators as well as operating rules and aggregation operators for picture fuzzy ˆ Z-number using algebraic T − N and T − CN .We utilize the average and geometric aggregation operators, comparing them with CoCo to Indicate the efficiency and functionality of our proposed technique. Through our investigation, particularly in decision-making contexts like Stock Market assessment, we underscore the significance of these operators and methodologies, particularly concerning Stock Market Prediction. We explore the relationship between uncertainty and randomness, enhancing our comprehension ofˆZofˆ ofˆZ-numbers and their capacity to handle uncertain data. Our research establishes a robust basis for better decision-making and uncertainty management across various fields by focusing on accuracy and precision.