Building Mamdani and Sugeno Fuzzy Inference Models in MQL5

Summary

This document explains how to use the FuzzyNet library in MQL5 to build fuzzy inference systems of the Mamdani or Sugeno type. It outlines a workflow: define input and output variables, assign linguistic terms and membership functions, create rules, provide input values, and calculate outputs. The library supports multiple membership-function shapes, rule parsing, and several defuzzification methods. For an unchanged Mamdani system, it describes defaults based on minimum implication, maximum aggregation, and center-of-gravity defuzzification.

The examples illustrate a service-tip estimator using Mamdani inference and a cruise-control regulator using Sugeno inference. They show application areas rather than trading results. The material is a software and modeling guide, not a validated trading strategy; it does not establish that fuzzy models produce predictive or profitable signals. Users must choose variables, membership functions, rules, and parameters for their problem, and the document gives no empirical evaluation, calibration procedure, or risk controls for financial use.

Key ideas

• FuzzyNet supports both Mamdani and Sugeno inference systems in MQL5.
• A model is built from variables, membership functions or Sugeno functions, and a set of rules.
• Mamdani systems can use configurable implication, aggregation, and defuzzification settings.
• The examples demonstrate a tip estimator and a cruise-control regulator rather than trading applications.
• The guide provides implementation concepts but no evidence of trading performance.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.