在眾多的理財工具中，股票投資是最為大家所熟悉且接受的。但投資人常常聽信從報章雜誌及財經節目上分析師所提供未經確認的消息來買賣股票。其中因為資訊少又無法判斷訊息的真偽，常常導致投資虧損。對於一般的投資者而言，某產業是否已經走下坡，或者某企業的競爭力是否已經逐漸下降，若只能透過新聞媒體得知消息，通常都會錯失買賣股票的最佳時機。
現行投資環境詭變多端，不同的情況下適合不同的投資判斷工具，如何能在複雜的環境裡掌握局勢，隨時動態產生新的投資策略，即可獲得優渥的風險溢酬，亦即若可以適時的採用不同投資環境偵測工具，正確的判斷出選股、擇時和資金分配策略，則投資人將可獲得不錯的超額報酬。
本研究將利用演化策略透過歷史資料的訓練和測試以獲得選股、擇時以及資金配置各個關鍵策略變數的範圍，再將此演化後的最佳變數範圍做為偵測下一階段投資環境的指標，即可判斷出在面對當前不停變化的股市環境下，可以正確挑選出適合的選股、擇時及資金配置策略，並套用在股市投資當中，幫助投資人做出正確的決策。

Among all wealth management tools, stock investment is not only widely accepted but also the most familiar tool to people. Unfortunately, however, investors often believe in unreliable and unconfirmed information from newspapers, magazines, and financial analysts to buy and sell stocks. Since the lack of information and the inability to judge the authenticity of the information, investors often end up with investment losses. For general investors, they usually miss the best timing to buy and sell stocks if news such as whether an industry has gone downhill or whether the competitiveness of a certain company has gradually declined can only be heard from news media.
Since current investment environment is changing, different conditions are correspond with different investment judgment tools. If one is able to dominate the complex environment and generate new investment strategies at any time, one can gain risk premium. In other words, investors will receive good excess returns by accurately using different investment environment detection tools to determine selection, timing, and capital allocation strategies.
This study will use evolutionary strategies to train and test historical data and further obtain a range of strategic variables for selection, timing, and capital allocation. In addition, we will be able to use this evolved optimal variable range as a detection of the next phase of the investment environment. The indicators can be used to determine the right selection, timing, and capital allocation strategies in the current stock market environment and be applied to the stock market investment to help investors to make the right decisions.

目錄
 第一章	緒論	1
 第二章	文獻探討	3
2.1.	選股	5
2.1.1.	巴菲特選股指標	5
2.1.2.	彼得林區選股指標	6
2.2.	擇時	8
2.2.1.	Ohlson評價模型	8
2.2.2.	多因子資本資產定價模型	11
2.2.3.	套利定價理論	13
2.3.	資金配置	14
2.3.1.	凱利公式	14
2.3.2.	最佳化F值	15
2.4.	類神經網路	16
2.5.	演化策略	18
 第三章 	研究架構	21
3.1.	選股策略	24
3.1.1.	巴菲特選股標準	24
3.1.2.	彼得林區選股標準	25
3.2.	擇時策略	26
3.2.1.	Ohlson model	27
3.2.2.	多因子CAPM	28
3.2.3.	APT	29
3.3.	資金配置策略	30
3.3.1.	凱利公式	31
3.3.2.	最佳化F值	31
3.4.	演化策略—選股和擇時策略變數範圍擷取	32
3.4.1.	染色體編碼	32
3.4.2.	染色體評估	33
3.5.	倒傳遞類神經網路—擇時策略	34
3.6.	演化策略—資金配置最佳化	34
3.6.1.	染色體編碼	34
3.6.2.	染色體評估	35
 第四章	實驗分析	37
4.1.	資料來源	37
4.2.	整合投資策略	38
4.3.	實驗結果—買賣訊號	40
4.4.	實驗結果—選擇策略	44
4.5.	實驗結果—與各指數比較獲利能力	75
 第五章	結論與未來展望	84
參考文獻	85


 
圖目錄
圖2 1類神經網路架構圖	17
圖2 2演化策略流程圖	19
圖3 1研究架構	22
圖3 2學習、偵測與決定流程	23
圖3 3資金配置流程	31
圖3 4染色體編碼—選股	32
圖3 5染色體編碼—擇時	33
圖3 6染色體編碼—資金配置	34
圖4 1實驗架構	38
圖4 2 2008年報酬率(週)	45
圖4 3 2009年報酬率(週)	47
圖4 4 2010年報酬率(週)	49
圖4 5 2011年報酬率(週)	51
圖4 6 2012年報酬率(週)	53
圖4 7 2013年報酬率(週)	55
圖4 8 2014年報酬率(週)	57
圖4 9 2015年報酬率(週)	59
圖4 10 2016年報酬率(週)	61
圖4 11 2017年報酬率(週)	63
圖4 12 2018年報酬率(週)	65

 
表目錄
表3 1演化策略參數設定表—選股	33
表3 2演化策略參數設定表—擇時	33
表3 3類神經預測買賣訊號之資料截圖	34
表3 4演化策略參數設定表—資金配置	36
表4 1八大類股代表股	37
表4 2 2008年買賣訊號準確率	40
表4 3 2009年買賣訊號準確率	40
表4 4 2010年買賣訊號準確率	41
表4 5 2011年買賣訊號準確率	41
表4 6 2012年買賣訊號準確率	41
表4 7 2013年買賣訊號準確率	42
表4 8 2014年買賣訊號準確率	42
表4 9 2015年買賣訊號準確率	42
表4 10 2016年買賣訊號準確率	43
表4 11 2017年買賣訊號準確率	43
表4 12 2018年買賣訊號準確率	43
表4 13各年買賣訊號平均準確率(單位：百分比)	44
表4 14 2008年投資策略(週)	44
表4 15 2009年投資策略(週)	46
表4 16 2010年投資策略(週)	48
表4 17 2011年投資策略(週)	50
表4 18 2012年投資策略(週)	52
表4 19 2013年投資策略(週)	54
表4 20 2014年投資策略(週)	56
表4 21 2015年投資策略(週)	58
表4 22 2016年投資策略(週)	60
表4 23 2017年投資策略(週)	62
表4 24 2018年投資策略(週)	64
表4 25 2017年Ohlson策略變數範圍—必要持股(週)	66
表4 26 2017年巴菲特策略變數範圍—每股盈餘(週)	67
表4 27 2017年資金配置百分比比例(週)	69
表4 28 2008年投資策略(月)	70
表4 29 2009年投資策略(月)	70
表4 30 2010年投資策略(月)	71
表4 31 2011年投資策略(月)	71
表4 32 2012年投資策略(月)	72
表4 33 2013年投資策略(月)	72
表4 34 2014年投資策略(月)	72
表4 35 2015年投資策略(月)	73
表4 36 2016年投資策略(月)	73
表4 37 2017年投資策略(月)	74
表4 38 2018年投資策略(月)	74
表4 39 2017年Ohlson策略變數範圍—必要持股(月)	75
表4 40 2017年巴菲特策略變數範圍—每股盈餘(月)	75
表4 41 2017年資金配置百分比比例(月)	75
表4 42 2008年與各指數報酬率比較表(單位：百分比)	76
表4 43 2009年與各指數報酬率比較表(單位：百分比)	77
表4 44 2010年與各指數報酬率比較表(單位：百分比)	77
表4 45 2011年與各指數報酬率比較表(單位：百分比)	78
表4 46 2012年與各指數報酬率比較表(單位：百分比)	79
表4 47 2013年與各指數報酬率比較表(單位：百分比)	79
表4 48 2014年與各指數報酬率比較表(單位：百分比)	80
表4 49 2015年與各指數報酬率比較表(單位：百分比)	80
表4 50 2016年與各指數報酬率比較表(單位：百分比)	81
表4 51 2017年與各指數報酬率比較表(單位：百分比)	81
表4 52 2018年與各指數報酬率比較表(單位：百分比)	82
表4 53各年平均報酬率(單位：百分比)	82

1.	Ahmad, M. I., Guohui, W., Rafiq, M. Y., Hasan, M., &Sattar, A. (2017). Assesing Performance of Moving Average Investment Timing Strategy Over the UK Stock Market. The Journal of Developing Areas, 51(3), 349-362.
2.	Azar, P. D., & Lo, A. W. (2016). The wisdom of twitter crowds: Predicting stock market reactions to fomc meetings via twitter feeds. The Journal of Portfolio Management, 42(5), 123-134.
3.	Baek, S., & Bilson, J. F. (2015). Size and value risk in financial firms. Journal of Banking & Finance, 55, 295-326.
4.	Bernard, V. L. (1995). The Feltham‐Ohlson framework: implications for empiricists. Contemporary Accounting Research, 11(2), 733-747.
5.	Beyer, H. G., Finck, S., & Breuer, T. (2014). Evolution on trees: On the design of an evolution strategy for scenario-based multi-period portfolio optimization under transaction costs. Swarm and Evolutionary Computation, 17, 74-87.
6.	Bonde, G., & Khaled, R. (2012, January). Stock price prediction using genetic algorithms and evolution strategies. In Proceedings of the International Conference on Genetic and Evolutionary Methods (GEM) (p. 1). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp).
7.	Campbell, J. Y., Giglio, S., Polk, C., & Turley, R. (2018). An intertemporal CAPM with stochastic volatility. Journal of Financial Economics, 128(2), 207-233.
8.	Chang, Y. H., & Wang, S. C. (2013). Integration of Evolutionary Computing and Equity Valuation Models to Forecast Stock Values Based on Data Mining. Asia Pacific Management Review, 18(1), 63-78.
9.	Charumathi, B., &Suraj, E. S. (2014). Refining Ohlson Model for Valuing Bank Stocks-An Artificial neural network Approach. Independent Business Review, 7(2), 32.
10.	Chen, Y., Mabu, S., &Hirasawa, K. (2011). Genetic relation algorithm with guided mutation for the large-scale portfolio optimization. Expert Systems with Applications, 38(4), 3353-3363.
11.	Chien, Y. W. C., & Chen, Y. L. (2010). Mining associative classification rules with stock trading data–A GA-based method. Knowledge-Based Systems, 23(6), 605-614.
12.	Chiu, D. Y., &Chian, S. Y. (2010, August). Exploring stock market dynamism in multi-nations with genetic algorithm, support vector regression, and optimal technical analysis. In Networked Computing and Advanced Information Management (NCM), 2010 Sixth International Conference on (pp. 694-699). IEEE.
13.	Deb, K. (2001). Multi-objective optimization using evolutionary algorithms (Vol. 16). John Wiley & Sons.
14.	Docherty, P., Chan, H., & Easton, S. (2013). Can we treat empirical regularities as state variables in the ICAPM? Evidence from Australia. Pacific-Basin Finance Journal, 22, 107-124.
15.	Hermes, A., & Maier-Paape, S. (2017). Existence and Uniqueness for the Multivariate Discrete Terminal Wealth Relative. Risks, 5(3), 44.
16.	Huang, L., & Wang, Z. (2014). Is the investment factor a proxy for time-varying investment opportunities? The US and international evidence. Journal of Banking & Finance, 44, 219-232.
17.	James, P., Cheh, J. J., & Kim, I. W. (2014). A comparative analysis on performance of seven all star investment models. Pan-Pacific Journal of Business Research, 5(2), 23.
18.	Kartikasari, D. (2016). A Test of Graham's and Lynch's Stock Screening Criteria on Shares Traded on the Indonesian Stock Exchange (Idx).
19.	Kelly, J. (1956) A New Interpretation of Information Rate. Bell System Technical Journal , 35, 917-926.
20.	Kocak, H. (2014). Canonical Coalition Game Theory for Optimal Portfolio Selection. Asian Economic and Financial Review, 4(9), 1254.
21.	Kuo, C. Y. (2017). Is the accuracy of stock value forecasting relevant to industry factors or firm-specific factors? An empirical study of the Ohlson model. Review of Quantitative Finance and Accounting, 49(1), 195-225.
22.	Lee, S. C., Lin, C. T., & Chang, P. T. (2011). An Ohlson valuation framework for valuing corporate governance: The case of Taiwan. Pacific-Basin Finance Journal, 19(4), 420-434.
23.	Lynch, P. S., Lynch, P., & Rothchild, J. (2000). One up on Wall Street: how to use what you already know to make money in the market. Simon and Schuster.
24.	Ma, J., & Wang, Y. (2015). Technical Analysis, Business Cycle, and Stock Market Returns. Advances in Management and Applied Economics, 5(2), 43.
25.	Madhogarhia, P. K., & Lam, M. (2015). Dynamic asset allocation. Journal of Asset Management, 16(5), 293-302.
26.	Mahapatra, S., &Bhaduri, S. N. (2018). Dynamics of the impact of currency fluctuations on stock markets in India: Assessing the pricing of exchange rate risks. Borsa Istanbul Review.
27.	Menacer, A., &Nurein, S. A. (2018). MACROECONOMIC VARIABLES AND ISLAMIC BANK STOCK RETURNS: PANEL DATA EVIDENCE FROM GCC COUNTRIES. International Journal of Information, Business and Management, 10(1), 214-229.
28.	Merton, R. C. (1973). An intertemporal capital asset pricing model. Econometrica: Journal of the Econometric Society, 867-887.
29.	Moghaddam, A. H., Moghaddam, M. H., &Esfandyari, M. (2016). Stock market index prediction using artificial neural network. Journal of Economics, Finance and Administrative Science, 21(41), 89-93.
30.	Niaki, S. T. A., &Hoseinzade, S. (2013). Forecasting S&P 500 index using artificial neural networks and design of experiments. Journal of Industrial Engineering International, 9(1), 1.
31.	Ohlson, J. A. (1995). Earnings, book values, and dividends in equity valuation. Contemporary accounting research, 11(2), 661-687.
32.	Ouysse, R., & Kohn, R. (2010). Bayesian variable selection and model averaging in the arbitrage pricing theory model. Computational Statistics & Data Analysis, 54(12), 3249-3268.
33.	Peterson, P. P. (1989). Event studies: A review of issues and methodology. Quarterly journal of business and economics, 36-66.
34.	Qiu, M., & Song, Y. (2016). Predicting the direction of stock market index movement using an optimized artificial neural network model. PloS one, 11(5), e0155133.
35.	Repoussis, P. P., Tarantilis, C. D., Bräysy, O., &Ioannou, G. (2010). A hybrid evolution strategy for the open vehicle routing problem. Computers & Operations Research, 37(3), 443-455.
36.	Ross, Stephen A., 1976, The arbitrage theory of capital asset pricing, Journal of Economic Theory 13, 341-360.
37.	Sahin, U., &Ozbayoglu, A. M. (2014). TN-RSI: Trend-normalized RSI indicator for stock trading systems with evolutionary computation. Procedia Computer Science, 36, 240-245.
38.	Schwefel, H. P. (1977). Numerische Optimierung von Computer-Modellen mittels der Evolutionsstrategie: mit einer vergleichenden Einführung in die Hill-Climbing-und Zufallsstrategie. Birkhäuser.
39.	Verma, A., & Kumar, C. V. R. S. (2015). A Test of the Arbitrage Pricing Theory in the Bombay Stock Market. FIIB Business Review, 4(2), 45-52.
40.	Vince, R. (2009). The leverage space trading model: reconciling portfolio management strategies and economic theory (Vol. 425). John Wiley and Sons.
41.	Vince, R. (2011), Optimal f and the Kelly Criterion, IFTA Journal 11, 21–28.
42.	Weigand, R. A., & Irons, R. (2007). The market p/e ratio, earnings trends, and stock return forecasts. The Journal of Portfolio Management, 33(4), 87-101.
43.	Ye, Y. (2013), "Application of the stock selection criteria of three value investors, Benjamin Graham, Peter Lynch, and Joel Greenblatt: a case of Shanghai stock Exchange from 2006-2011", Internal Journal of Scientific and Research Publications, Vol. 3 No.8, pp. 2250-3153.
44.	Yilan, B. (2011). Stock Market Prediction Model Based on Genetic Algorithm and Support Vector Regression. Energy Procedia, (11), 4025-4029.
45.	Yodmun, S., &Witayakiattilerd, W. (2016). Stock Selection into Portfolio by Fuzzy Quantitative Analysis and Fuzzy Multicriteria Decision Making. Advances in Operations Research, 2016.
46.	Zakamulin, V. (2014). The real-life performance of market timing with moving average and time-series momentum rules. Journal of Asset Management, 15(4), 261-278.
47.	王恆娟. (2012). 彼得林區擇股法是否適用於台灣股市?. 淡江大學管理科學學系企業經營碩士在職專班學位論文, 1-34.
48.	吳博欽, & 鄭哲惠. (2006). 企業生命週期, 產業別與股權評價: Real Option 與 Ohlson Model 之比較. 會計評論, (43), 95-121.
49.	李雅璇. (2013). 以巴菲特選股模式建構基本面投資組合: 在台股之實證研究. 國立中央大學, 碩士論文.
50.	高惠娟, 王澤維, &陳建葦. (2013). 價值型投資策略之探討-以本益比, 市價淨值比, 市價銷貨比為例. 嶺東學報, (34), 1-35.
51.	康譽騰. (2012). 運用基因演算法建立不同時期之最佳選股模式. 元智大學資訊管理學系學位論文, 1-61.
52.	張淑芳譯，Warren E. Buffet & Lawrence A. Cunningham 著，巴菲特寫給股東的信，台北:財訊出版社，2002 年。
53.	張婷容（2008）。凱利準則及其在賭博上的應用. 國立中央大學數學研究所碩士論文, 桃園縣.
54.	張應華, &黃偵維. (2011). 整合價值評估模式與交易策略於股票投資應用. 第二十二屆國際資訊管理學術研討會, 臺中.
55.	陳尚武, 顏榳均, 莊可欣, &黃麟翔. (2015). 投資風格對風險調整報酬的影響-台股之實證分析. 東亞論壇, (488), 27-37.
56.	陳釗而, &林奎甫. (2015). 以追蹤資料分量迴歸方式衡量台灣股市預期報酬與風險關係. 經濟論文叢刊, 43(3), 297-331.
57.	黃國鳴. (2017). 基因表達規劃法於台指期貨動態資金管理之研究. 輔仁大學資訊管理學系碩士在職專班學位論文, 1-201.
58.	鄧安鎮. (2007). 巴菲特價值型選股模式在台股應用之研究. 逢甲大學, 台中市.
59.	鄭敦維. (2011). 一個基植於遺傳演算法與模糊理論最佳化之支援向量機選股模型. 高雄大學, 碩士論文.
60.	謝耀德. (2009). 彼得林區價值型選股模式於台灣股市之應用. 逢甲大學經營管理碩士在職專班學位論文, 1-93.
61.	鐘麗文. (2014). 選股策略-台灣股市之實證研究. 中山大學經濟學研究所學位論文, 1-46.