Abstract

This paper adopts the multi-criterion decision-making model of fuzzy-TODIM and genetic algorithm (GA) for optimal portfolio allocation. We applied Markowitz’s portfolio parameters as inputs for the fuzzy TODIM model to rank stocks that are constituents of each index from three different markets. Portfolios are then generated dynamically using three weighting techniques and subject to multi-objective criteria and additional constraints. The results indicate a significant variation in performance metrics between the model-generated portfolios and the market indices. Replication of the procedure produces a similar outcome. Moreover, the out-of-sample tests conducted over 3 years validate the results’ robustness, indicating that fuzzy TODIM, combined with GA, can achieve superior performance in dynamic portfolio allocation.

中文翻译：

---

使用模糊 TODIM、遗传算法和多标准约束进行鲁棒投资组合优化

摘要

本文采用模糊TODIM多准则决策模型和遗传算法（GA）进行最优投资组合配置。我们应用马科维茨的投资组合参数作为模糊 TODIM 模型的输入，对来自三个不同市场的每个指数的成分股进行排名。然后使用三种加权技术动态生成投资组合，并遵守多目标标准和附加约束。结果表明模型生成的投资组合与市场指数之间的绩效指标存在显着差异。重复该过程会产生类似的结果。此外，历时3年的样本外测试验证了结果的稳健性，表明模糊TODIM结合遗传算法在动态投资组合配置中可以取得优异的性能。