應用自組織映射圖神經網路於國內開放式股票型基金市場之研究

Abstract

共同基金是大眾投資人最常接觸的金融投資商品，在國內金融市場上約從2000年起，資金的規模程度呈現爆發性的成長，投資人的資金投入量與日俱增。愈來愈多的研究學者投入研究共同基金的績效行列，傳統的績效評估模型，早期從Treynor指標(1965)、Sharpe指標(1966)及Jensen指標(1968)開始，對當時的投資人而言是一種明確的選擇基金參考指標。然而，關於共同基金的績效評估，後期發展出各種基金績效評估法則，至今仍無一明確的評判標準。因此如何正確地衡量共同基金的績效，藉以選擇優勢的基金將是未來投資基金成敗最重要的一個關鍵因素。

近年來，人工智慧方法學在財務金融領域上之應用蓬勃發展，本研究嘗試運用人工智慧領域中之無監督式學習的自組織映射圖神經網路來建立選擇優勢基金的模型。以2000年至2010年為研究期間，國內開放式股票型共同基金為研究對象，共選取100檔。以每個月初前30日之每日的前30日、60日、90日基金淨值與台灣加權股價指數的相對報酬率當作基金績效的評估指標，月份為分群的單位，最後依據每群的優勝率或平均報酬率來挑選優勢的基金，並依此模型進行投資交易模擬。

實證研究結果顯示，以共同基金淨值與台灣加權股價指數的相對報酬率作為自組織映射圖神經網路的輸入變數，除了可發現優勢的基金外並且具有良好的預測能力。採用本模型選擇的優勢基金進行投資交易模擬，會優於隨機交易模型且擊敗大盤。實驗過程中亦發現當投資模擬區間設定在三個月的獲利能力最高，由此可以推論採用本模型操作時較適合運用在短中期的投資。希望藉由此研究之發現，能輔助投資者在面對瞬息萬變的金融環境下做出正確的投資決策。

Mutual Fund is one of the most well-known financial investment products among public investors. In the domestic financial market from the year 2000, the scale of the extent of funds has shown explosive growth, and the investor's capital investment is growing rapidly. More and more experts start to conduct research on the ranks of mutual fund performance, and the traditional performance evaluation models, early from the Treynor Index (1965), Sharpe Index (1966) and Jensen index (1968). Those are a clear performance evaluation index for investors to choose fund at that time. However, with regard to mutual fund performance, there is still no clear criteria for the recent development of a variety of fund performance evaluation rules. So how to properly measure the performance of mutual funds is the key factor for future successful investment.

Recently, the application of the artificial intelligence approaches in the field of finance is developed enormously. This research, applies artificial intelligence of unsupervised learning self-organizing map neural network to establish a model to select the superior funds. The study period is from year 2000 to 2010 and picks 100 domestic equity mutual funds as study object. We use 30 days prior to the beginning of each month’s prior 30 days, 60 days, 90 days on fund’s net asset value and the Taiwan Weighted Stock Index (TAIEX) return as the fund’s relative performance evaluation indicators classified by month. Finally, based on the superior rate or the average return rate, we select the superior funds and simulate investment transactions according to this model.

The empirical results show that using the mutual fund’s net asset value and the TAIEX’s relative return as self-organizing map neural network input variables not only finds out the superior fund but also has a good predictive ability. Applying this model to simulate investment transactions will be better than the random trading model and beats the market. The experiments also found that the investment simulation of a three-month interval has the highest profitability. The model operation suggests that it is more suitable for short-term and medium-term investment. This research can assist investors to make the right investment decisions while they face the rapid change of financial environment.