建設類公司普遍存在高風險經營之特性，且其經營績效易受政策影響，加上財報採用「全部完工認列」方式認列獲利，銷售營收不易預估，連帶造成建設類股於市場中不受投資人青睞，許多建設業的優質公司價值被低估，對產業資本結構與發展造成衝擊，鑑於上述原因，針對建設類股建置一個全面且可實際執行的選股策略模型，以降低建設類股投資門檻，有其必要性與急迫性。本研究透過網路爬蟲程式爬取臺灣上市櫃每日收盤行情資料、月營收資料及財務報表資料，進而自動計算獲利能力、成本費用率、每股比率、成長率、償債能力、經營能力等六大面向共計48個基本面財務指標，使用機器學習演算法交併挑選具有解釋能力的基本面指標後，以FBI演算法進行選股指標條件優化，並採三種具代表性的投資組合權重優化模型進行報酬績效比較，從中選取表現最佳的權重分配模型。歷史回測顯示，本研究所提出之啟發式演算法優化多因子投資組合模型，於臺灣上市櫃建設類股與全部類股均適用，可有效且穩定地獲取優於市售股票型基金之超額報酬。其中，建設類股以獲利能力面財務指標：ROE稅後，選股策略表現最佳，全部類股則主要以成本費用率面財務指標：研究發展費用率，具有最佳的篩選性。
本研究之分析結果顯示：建設類股投資組合具有基期低、易入手及抗跌之特性適合散戶投資人操作，即使不具備金融投資專業知識的投資人也可採用本研究所提出之整體最佳選股策略以相對較低之風險穩定獲取高於市場績效的超額報酬。研發的雛型成果亦可提供專業投資顧問或證券投資機構作為初步投資組合篩選之工具，配合其自身專業概念及市場分析混合搭配各種投資組合權重分配模型，靈活且自由地進行基金操盤。

The high-risk nature of the construction industry is exacerbated by its susceptibility to government policies. Since the implementation of International Financial Reporting Standards in 2013, Taiwanese construction companies have been permitted to report profits only when the ownership of the construction project has been transferred to a buyer. Under these conditions, it has been difficult to predict the sales revenue of construction companies, with the result that many high-quality construction firms are underrated by the market. Note that this has had a profound impact on the capital structure and development of the industry. This paper developed a comprehensive and practically executable stock selection model for the construction industry. Machine learning is used to guide the selection fundamental indicators toward factors with explanatory power, and the Forensic-Based Investigation algorithm (FBI) is used to optimize stock selection conditions. Three portfolio optimization models (Equal weighted, Mean-Variance, and Hierarchical risk parity) were adopted to further enhance the performance of our trading model. Out-of-sample back-testing results indicate that stocks in the construction industry are a viable investment, due to their low base period, easy acquisition, and resistance to abrupt drops during financial crises. This model can also be used as a tool by which to implement initial investment portfolio screening. In simulations, the proposed metaheuristic-optimized multi-factor-based trading model outperformed 0050TW and 0056TW in terms of stable excess returns.

Ab. Halim, M. S., Haniff, S., Mat Junoh, m. Z., & Osman, A. (2014). Financial Performance and the Management Issues of Bumiputera Construction Firms in the Malaysian Construction Industry. Journal of Scientific Research & Reports, 3.
Allen, F., & Karjalainen, R. (1999). Using genetic algorithms to find technical trading rules. Journal of financial economics, 51, 245-271.
Bauer, R. J. (1994). Genetic algorithms and investment strategies (Vol. 19): John Wiley & Sons.
Black, F., & Litterman, R. (1990). Asset allocation: combining investor views with market equilibrium. Goldman Sachs Fixed Income Research, 115.
Breiman, L. (2001). Random Forests. Machine Learning, 45, 5-32.
Buitinck, L., Louppe, G., Blondel, M., Pedregosa, F., Mueller, A., Grisel, O., Niculae, V., Prettenhofer, P., Gramfort, A., & Grobler, J. (2013). API design for machine learning software: experiences from the scikit-learn project. arXiv preprint arXiv:.
Bustos, O., & Pomares-Quimbaya, A. (2020). Stock market movement forecast: A Systematic review. Expert Systems with Applications, 156, 113464.
Chen, S., Montgomery, J., & Bolufé-Röhler, A. (2015). Measuring the curse of dimensionality and its effects on particle swarm optimization and differential evolution. Applied Intelligence, 42, 514-526.
Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). San Francisco, California, USA: Association for Computing Machinery.
Chen, W., Zhang, H., Mehlawat, M. K., & Jia, L. (2021). Mean–variance portfolio optimization using machine learning-based stock price prediction. Applied Soft Computing, 100, 106943.
Cheng, C.-H., Kao, Y.-F., & Lin, H.-P. (2021). A financial statement fraud model based on synthesized attribute selection and a dataset with missing values and imbalanced classes. Applied Soft Computing, 108, 107487.
Cheng, M.-Y., & Prayogo, D. (2014). Symbiotic Organisms Search: A new metaheuristic optimization algorithm. Computers & Structures, 139, 98-112.
Cheong, D., Kim, Y. M., Byun, H. W., Oh, K. J., & Kim, T. Y. (2017). Using genetic algorithm to support clustering-based portfolio optimization by investor information. Applied Soft Computing, 61, 593-602.
Choi, J.-K., Yoo, S.-K., Kim, J.-H., & Kim, J.-J. (2014). Capital Structure Determinants among Construction Companies in South Korea: A Quantile Regression Approach. Journal of Asian Architecture and Building Engineering, 13, 93-100.
Chou, J.-S., & Nguyen, N.-M. (2020). FBI inspired meta-optimization. Applied Soft Computing, 93, 106339.
Dai, Y., & Qin, Z. (2021). Multi-period uncertain portfolio optimization model with minimum transaction lots and dynamic risk preference. Applied Soft Computing, 109, 107519.
De Prado, M. L. (2016). Building diversified portfolios that outperform out of sample. The Journal of Portfolio Management, 42, 59-69.
DeMiguel, V., Garlappi, L., & Uppal, R. (2009). Optimal versus naive diversification: How inefficient is the 1/N portfolio strategy? The Review of Financial Studies, 22, 1915-1953.
Dong, S., Wang, J., Luo, H., Wang, H., & Wu, F.-X. (2021). A dynamic predictor selection algorithm for predicting stock market movement. Expert Systems with Applications, 186, 115836.
Duxbury, D., & Yao, S. (2017). Are investors consistent in their trading strategies? An examination of individual investor-level data. International Review of Financial Analysis, 52, 77-87.
Effrosynidis, D., & Arampatzis, A. (2021). An evaluation of feature selection methods for environmental data. Ecological Informatics, 61, 101224.
Emin Öcal, M., Oral, E. L., Erdis, E., & Vural, G. (2007). Industry financial ratios—application of factor analysis in Turkish construction industry. Building and Environment, 42, 385-392.
Fürnkranz, J. (2010). Decision Tree. In C. Sammut & G. I. Webb (Eds.), Encyclopedia of Machine Learning (pp. 263-267). Boston, MA: Springer US.
finlab-python.
Frank, M. Z., & Goyal, V. K. (2003). Testing the pecking order theory of capital structure. Journal of financial economics, 67, 217-248.
Green, R. C., & Hollifield, B. (1992). When Will Mean-Variance Efficient Portfolios Be Well Diversified? The Journal of Finance, 47, 1785-1809.
Guild, J. (2017). Fintech and the Future of Finance. Asian Journal of Public Affairs, 17-20.
Haq, A. U., Zeb, A., Lei, Z., & Zhang, D. (2021). Forecasting daily stock trend using multi-filter feature selection and deep learning. Expert Systems with Applications, 168.
He, H., Zhang, W., & Zhang, S. (2018). A novel ensemble method for credit scoring: Adaption of different imbalance ratios. Expert Systems with Applications, 98, 105-117.
Hillebrandt, P. M. (2000). Economic theory and the construction industry: Springer.
Huang, C.-F. (2012). A hybrid stock selection model using genetic algorithms and support vector regression. Applied Soft Computing, 12, 807-818.
. IFRSs正式上路 上市公司第一季財報應於5月15日前公告. In. (2013): 臺灣證券交易所.
Jorion, P. (1985). International portfolio diversification with estimation risk. Journal of Business, 259-278.
Kaczmarek, T., & Perez, K. (2021). Building portfolios based on machine learning predictions. Economic Research-Ekonomska Istraživanja, 1-19.
Kangari, R., Farid, F., & Elgharib Hesham, M. (1992). Financial Performance Analysis for Construction Industry. Journal of Construction Engineering and Management, 118, 349-361.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30, 3146-3154.
Ledoit, O., & Wolf, M. (2004). A well-conditioned estimator for large-dimensional covariance matrices. Journal of Multivariate Analysis, 88, 365-411.
Liu, M., Luo, K., Zhang, J., & Chen, S. (2021). A stock selection algorithm hybridizing grey wolf optimizer and support vector regression. Expert Systems with Applications, 179, 115078.
MARKOWITZ, H. (1952). PORTFOLIO SELECTION. The Journal of Finance, 7, 77-91.
Martin, R. A. (2021). PyPortfolioOpt: portfolio optimization in Python. Journal of Open Source Software, 6, 3066.
Rao, R. V., Savsani, V. J., & Vakharia, D. P. (2011). Teaching–learning-based optimization: A novel method for constrained mechanical design optimization problems. Computer-Aided Design, 43, 303-315.
Rao, R. V., Savsani, V. J., & Vakharia, D. P. (2012). Teaching–Learning-Based Optimization: An optimization method for continuous non-linear large scale problems. Information Sciences, 183, 1-15.
Son, H., Hyun, C., Phan, D., & Hwang, H. J. (2019). Data analytic approach for bankruptcy prediction. Expert Systems with Applications, 138, 112816.
Yang, X.-S. (2014). Nature-Inspired Optimization Algorithms. Oxford: Elsevier.
Yang, X.-S., Deb, S., Loomes, M., & Karamanoglu, M. (2013). A framework for self-tuning optimization algorithm. Neural Computing and Applications, 23, 2051-2057.
公開資訊觀測站. (Vol. 2021).
國際財務報導準則我國推動架構. (Vol. 2021): 臺灣證券交易所.
張金鶚, & 章定煊. (2001). 上市櫃建設公司績效評估與影響因素探討. In.
張智斌. (2020). 啟發式演算法優化多重輸出機器學習技術預測臺灣營建股價. 國立臺灣科技大學, 台北市.
章定煊. (2005). 上市櫃建設公司土地投資與開發策略對經營績效影響之探討. 住宅學報, 14, 41-65.
陳佳如. (2011). 實施打房措施對上市櫃建築投資公司股價之影響. 國立臺灣大學.
陳柏年. (2001). 應用遺傳演算法於財務指標選股策略之探討. 國立中央大學, 桃園縣.
臺灣經濟新報 財務資料庫 科目說明. (Vol. 2021).
臺灣證券交易所每日收盤行情. (Vol. 2021).
潘柏宇. (2016). 房地合一課稅對營建業股價影響之事件研究. 國立臺灣大學.
蔣婉柔. (2019). 台灣ETF投資組合配置之研究－改良後階層風險對等模型之應用. 國立臺灣大學.
盧麗安. (1996). 財務基本分析與臺灣股價表現. 國立中山大學, 高雄市.