|
 |
|
|
|
Unlocking Insights of Fuzzy Mathematics for Enhanced Predictive Modelling |
|
PP: 49-59 |
|
doi:10.18576/amis/190105
|
|
Author(s) |
|
Asokan Vasudevan,
N. Yogeesh,
Suleiman Ibrahim Mohammad,
N. Raja,
D. K Girija,
M. Rashmi,
Ahmad A. Abu-Shareha,
Muhammad Turki Alshurideh,
|
|
Abstract |
|
The many aspects of predictive modeling for financial market prediction and health diagnostics based on fuzzy mathematics are explored in this study. Two fuzzy logic-based models are designed and implemented using the popular method of managing uncertainties and linguistic variables: fuzzy logic. The initial model given for predicting financial markets used fuzzy sets, membership functions, and the resulting rules to capture relationships between sentiment measurement and market behavior in a complex manner. In turn, the model is linguistically interpretable, meaning that stakeholders can use its predictions as a fintech investment tool. These fuzzy rules, which connect the input variables to possible medical conditions, are extracted from expert knowledge and medical guidelines. The Fuzzy Inference System of the Sugeno type is flexible in dealing with complex relationships, which helps to produce accurate diagnostic outputs. Trust, in turn, is increased by the system’s ability to accept vague data and supply linguistic explanations for predictions and its dynamic model. Finally, it is interesting to note that the results suggest advantages of fuzzy mathematics in both cases concerning uncertainty management, incorporation of expert knowledge, and increasing interpretability. They provide insights for practical applications in financial analysis and medical diagnostics, future works on hybrid models, and broader uses of fuzzy mathematics techniques within the context of predictive modeling.
|
|
|
 |
|
|