本研究探討新加坡交易所日經225指數現貨盤後期貨之交易及美股指數對次日開盤現貨指數之影響,利用非現貨交易時段之日經225指數、現貨前一日之收盤指數及前一日Dow Jones、Nasdaq之收盤指數建構類神經網路預測模式,針對現貨開盤指數進行預測。而在類神經網路預測模式之建構方面,首先利用敏感度分析決定模式之參數,至於建構模式之穩健性評估方面,則利用訓練樣本佔所有樣本之不同資料比例加以分析。此外為了評估模式之預測效果,本研究以1998年10月1日至1999年12月31日現貨與期貨指數5分鐘日內資料及Dow Jones、Nasdaq之每日收盤指數為實証之時間序列資料。根據實証結果顯示,建構之類神經網路預測模式相較於以現貨前一日收盤指數為輸入變數之類神經網路模式、以現貨前一日之收盤指數為當日現貨開盤預測值之隨機漫步模型及ARIMA模式顯著有較好之預測能力,顯示非現貨交易時段之期貨交易價格及美股之Dow Jones、Nasdaq之收盤指數內含豐富之資訊,可以做為預測現貨開盤指數之參考。
This study investigates the influence of SGX-DT Nikkei 225 futures prices during the non-cash-trading (NCT) period, Dow Jones and Nasdaq's closing index to the Nikkei 225 opening cash price index. NCT futures at 07:55, previous day's cash market closing index at 14:00, Dow Jones and Nasdaq's closing index are used to forecast the 08:00 opening cash price index by the neural networks model. Sensitivity analysis is first employed to address and solve the issue of finding the appropriate setup of the topology of the networks. Extensive studies are then performed on the robustness of the constructed network by using different training and testing sample sizes. To demonstrate the effectiveness of our proposed method, the five-minute intraday data of spot and futures index as well as Dow Jones and Nasdaq's closing index from October 1, 1998 to December 31, 1999 was evaluated using the designed neural network model. Analytic results demonstrate that the proposed neural networks model outperforms the neural network model with previous day's closing index as the input variable, the random walk model and ARIMA forecasts. It therefore indicates that there is valuable information involved in the futures prices during the NCT period and Dow Jones as well as Nasdaq's closing index in forecasting the opening cash price index.