This paper introduces a market-inspired meta-heuristic named the Market Game Optimization Algorithm (MGOA), which models the symmetric competitive interactions between merchants and customers. MGOA simulates the dual dynamics of attraction and collaboration among merchants and customers, integrating a global search strategy that reflects how merchants attract customers. The optimization process includes two distinct stages, each employed with a 50% probability through a merchant cooperation mechanism designed to balance exploration and exploitation. Prior to performance evaluation, a qualitative analysis and parameter sensitivity study were conducted to clarify parameter selection and optimization characteristics. The algorithm was tested on 42 benchmark functions from the CEC2017 and CEC2022 test suites and compared against 10 well-established and 10 recently proposed meta-heuristic algorithms. Results indicate that MGOA achieves the highest overall ranking. Furthermore, its application to 11 real-world engineering design problems demonstrates high effectiveness and solution quality. All experimental findings confirm that MGOA is a robust and competitive meta-heuristic capable of solving complex real-world optimization problems.

As artificial intelligence becomes increasingly integrated into education, intelligent tutoring systems (ITSs) are emerging as important tools for personalized language learning. However, high learner dropout rates indicate that sustaining continuous intention remains a key challenge. This study examines the mechanisms and differential effects shaping IELTS learners’ continuous intention to use ITSs in listening and reading contexts, using an AI test-preparation assistant and 494 valid responses from 522 Credamo surveys. PLS-SEM results show that perceived usefulness, perceived ease of use, perceived enjoyment, and self-efficacy significantly improve learning attitude, while learning attitude and self-efficacy further strengthen continuous intention. Multi-group analysis reveals contextual differences: perceived enjoyment has a stronger effect in listening (β = 0.340, p < 0.001) than in reading (β = 0.178, p < 0.01), whereas perceived usefulness has a stronger effect in reading (β = 0.424, p < 0.001) than in listening (β = 0.226, p < 0.001). ANN results confirm that enjoyment is the strongest predictor of learning attitude in listening (normalized importance = 100%), while usefulness is the key predictor in reading (normalized importance = 100%). The study extends the TAM by incorporating self-efficacy and perceived enjoyment and highlights the importance of context-specific ITS design for AI-supported language learning.