Enhanced Evaluation Model Based on Classification Selection Applied to Value Evaluation of Waste Household Appliances

In the process of recycling, dismantling, and reusing household appliances, implementing extended producer responsibility (EPR) has become increasingly important. Designing a reasonable pricing mechanism for waste appliance recycling is critical implementation EPR. To address problem labor-intensive experience-dependent traditional manual methods assessing value in this paper, we propose an evaluation method based on subtractive clustering adaptive neuro fuzzy inference system (SCM–ANFIS), which outperforms neural networks such as LSTM, BP network, random forest Takagi–Sugeno network (T–S FNN). Moreover, combine five aforementioned algorithms to design combination model maximum ratio (CEM–MRC), can achieve performance improvement 0.1% terms mean absolute percentage error (MAPE) compared suboptimal network. Furthermore, enhanced classification selection (EEM–CS) designed automatically select results between optimal SCM–ANFIS CEM–MRC, resulting 0.73% reduction MAPE 1.42% CEM–MRC. also validate proposed using dataset television demonstrates high accuracy assessment mechanisms achieved without human intervention significant conventional neural-network-based algorithms.