Computational Intuition: Machine Learning Models That Mimic Human Gut Feelings

Abstract: Computational intuition explores the frontier of machine learning by simulating human-like gut feelings and rapid decision-making under uncertainty. This paper investigates models that mimic intuitive responses by integrating neural heuristics, affective inference, and subconscious pattern detection. Drawing from psychology, neuroscience, and AI, we construct hybrid systems that replicate the heuristic reasoning humans deploy in real-time decision-making. Researcher evaluated multiple architectures using datasets from emotion-labeled decisions (IntuitionNet, Human Affect Forecast) and apply statistical techniques including logistic regression, accuracy benchmarks, and predictive modeling. Results show models using embedded affective priors and fast pattern generalization outperform traditional algorithms in uncertainty-heavy scenarios. Researcher findings provideda theoretical and practical framework for designing next-generation intuitive AI systems. Keywords: Computational intuition, intuitive AI, heuristic learning, affective computing, neural heuristics, subconscious modeling, decision-making, statistical analysis, machine intuition, gut-feeling prediction