本研究旨在探討影響尼龍6（PA6）價格波動的關鍵因素，並透過機器學習技術建立預測模型，以提高價格預測的準確性和穩定性。研究數據涵蓋了2018年至2024年間尼龍6及其相關原材料的價格變化，並運用了多種機器學習模型，包括線性迴歸、決策樹、隨機森林、極限梯度提升（XGBoost）及多層感知器（MLP）等，來比較不同模型的預測效能。
結果顯示，隨機森林模型在預測尼龍6價格方面具有最佳表現，其次為XGBoost模型。分析表明，影響尼龍6價格的最重要因素為其主要原料己內醯胺（Caprolactam），其次是下游產品尼龍絲紗（Nylon Filament）和競爭產品的價格。此外，研究結果也顯示，應用大型語言模型（LLM）進行價格預測的效能不如傳統的機器學習模型。
本研究證實了機器學習技術在價格預測上的優勢，尤其是在面對多變數和非線性數據時，隨機森林模型的泛化能力表現突出。透過分析這些關鍵變數，企業可更準確地制定報價策略，有效應對市場波動，提升競爭力。本研究結果不僅為學術界提供了有價值的參考，也為產業決策者提供了實際應用上的洞見。

This study aims to investigate the key factors influencing price fluctuations of Nylon 6 (PA6) and develop predictive models using machine learning techniques to enhance the accuracy and stability of price forecasts. The research data covers price variations of PA6 and its related raw materials from 2018 to 2024. Various machine learning models, including Linear Regression, Decision Trees, Random Forest, Extreme Gradient Boosting (XGBoost), and Multilayer Perceptron (MLP), were employed to compare their prediction performance.
The results indicate that the Random Forest model demonstrated the best performance in predicting PA6 prices, followed by the XGBoost model. The analysis revealed that the most significant factor affecting PA6 prices is its primary raw material, Caprolactam, followed by downstream product Nylon Filament and the prices of competitive products. Additionally, the study found that the performance of Large Language Models (LLMs) in price prediction was inferior to traditional machine learning models.
This research confirms the superiority of machine learning techniques in price forecasting, particularly when dealing with multi-variable and nonlinear data, with the Random Forest model exhibiting outstanding generalization capabilities. By analyzing these key variables, businesses can more accurately formulate pricing strategies, effectively respond to market fluctuations, and enhance their competitiveness. The findings of this study provide valuable insights not only for academia but also for industry decision-makers.

論文審定書i
誌謝ii
摘要iii
Abstractiv
目錄v
圖次vii
表次viii
第壹章緒論1
第一節 研究背景1
第二節 研究動機2
第三節 研究目的3
第貳章文獻探討5
第一節 價格預測方法5
第參章研究方法與步驟13
第一節 研究流程步驟13
第二節 數據前處理13
第三節 數據集劃分13
第四節 機器學習模型訓練14
第五節 應用大型語言模型（LLM）進行預測14
第六節 模型評估與最佳模型選擇14
第肆章實證與分析15
第一節 資料整理描述15
第二節 重要變數分析16
第三節 模型結果17
第伍章研究結論與建議20
第一節 研究結論20
第二節 限制與建議21
第陸章參考文獻23

Adetunji, A. B., Akande, O. N., Ajala, F. A., Oyewo, O., Akande, Y. F., & Oluwadara, G. (2022). House price prediction using random forest machine learning technique. Procedia Computer Science, 199, 806-813.
An, J., Mikhaylov, A., & Moiseev, N. (2019). Oil price predictors: Machine learning approach. International Journal of Energy Economics and Policy, 9(5), 1-6.
Chen, E., & He, X. J. (2018). Crude Oil Price Prediction with Decision Tree Based Regression Approach. Journal of International Technology and Information Management, 27(4), COV1-COV1.
Chen, Q., Zhang, W., & Lou, Y. (2020). Forecasting stock prices using a hybrid deep learning model integrating attention mechanism, multi-layer perceptron, and bidirectional long-short term memory neural network. IEEE Access, 8, 117365-117376.
Costa, A. B. R., Ferreira, P. C. G., Gaglianone, W. P., Guillén, O. T. C., Issler, J. V., & Lin, Y. (2021). Machine learning and oil price point and density forecasting. Energy Economics, 102, 105494.
Demirer, R., Gkillas, K., Gupta, R., & Pierdzioch, C. (2022). Risk aversion and the predictability of crude oil market volatility: A forecasting experiment with random forests. Journal of the Operational Research Society, 73(8), 1755-1767.
Do, K. D. (2021). Evaluating the competitiveness of the vietnam textile and garment industry. Journal of International Business and Management, 4(10), 01-13.
Fan, X., Wang, L., & Li, S. (2016). Predicting chaotic coal prices using a multi-layer perceptron network model. Resources Policy, 50, 86-92.
Fazli, M. S., & Lebraty, J.-F. (2013). A comparative study on forecasting polyester chips prices for 15 days, using different hybrid intelligent systems. The 2013 International Joint Conference on Neural Networks (IJCNN),
Jabeur, S. B., Khalfaoui, R., & Arfi, W. B. (2021). The effect of green energy, global environmental indexes, and stock markets in predicting oil price crashes: Evidence from explainable machine learning. Journal of Environmental Management, 298, 113511.
Jabeur, S. B., Mefteh-Wali, S., & Viviani, J.-L. (2024). Forecasting gold price with the XGBoost algorithm and SHAP interaction values. Annals of Operations Research, 334(1), 679-699.
Kocaoğlu, D., Turgut, K., & Konyar, M. Z. (2022). Sector-Based Stock Price Prediction with Machine Learning Models. Sakarya University Journal of Computer and Information Sciences, 5(3), 415-426.
Krause, B., Kroschwald, L., & Pötschke, P. (2019). The influence of the blend ratio in PA6/PA66/MWCNT blend composites on the electrical and thermal properties. Polymers, 11(1), 122.
Lopez-Lira, A., & Tang, Y. (2023). Can chatgpt forecast stock price movements? return predictability and large language models. arXiv preprint arXiv:2304.07619.
Mei, J., He, D., Harley, R., Habetler, T., & Qu, G. (2014). A random forest method for real-time price forecasting in New York electricity market. 2014 IEEE PES general meeting| conference & exposition,
Namdari, A., & Li, Z. S. (2018). Integrating fundamental and technical analysis of stock market through multi-layer perceptron. 2018 IEEE technology and engineering management conference (TEMSCON),
Nwulu, N. I. (2017). A decision trees approach to oil price prediction. 2017 International Artificial Intelligence and Data Processing Symposium (IDAP),
Safari, A., & Davallou, M. (2018). Oil price forecasting using a hybrid model. Energy, 148, 49-58.
Thaore, V., Chadwick, D., & Shah, N. (2018). Sustainable production of chemical intermediates for nylon manufacture: A techno-economic analysis for renewable production of caprolactone. Chemical Engineering Research and Design, 135, 140-152.
Thomassey, S., Happiette, M., & Castelain, J.-M. (2005). A global forecasting support system adapted to textile distribution. International Journal of Production Economics, 96(1), 81-95.
Xiao, C., Leng, X., Zhang, X., Zheng, K., & Tian, X. (2018). Improved thermal properties by controlling selective distribution of AlN and MWCNT in immiscible polycarbonate (PC)/Polyamide 66 (PA66) composites. Composites Part A: Applied Science and Manufacturing, 110, 133-141.
Xu, X., Yao, B., Dong, Y., Gabriel, S., Yu, H., Hendler, J., Ghassemi, M., Dey, A. K., & Wang, D. (2024). Mental-llm: Leveraging large language models for mental health prediction via online text data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 8(1), 1-32.