本文利用130個預測變數與七種機器學習模型，針對台指選擇權213個樣本外月份（2007–2024年），探討隱含波動率曲面（IVS）動態的樣本外預測力。依據 Collin-Dufresne et al.（2023）的二次迴歸架構萃取具有經濟意義的IVS因子 : 水準、斜率與曲率後，本文揭示出一個鮮明的不對稱性：水準因子不可預測，而斜率與曲率因子則具有高度可預測性（Elastic Net的樣本外R²分別為+17.85%與+14.32%，p均小於0.001）。三項核心發現如下：其一，稀疏性在高維度環境中至關重要，Elastic Net僅從130個預測變數中選取5至10個，預測表現遠超Ridge（+4.34%），顯示在真實訊號稀疏的情況下，ℓ₁正則化（而非單純的係數縮減）方為關鍵。其二，相較於主成分分析（PCA），二次迴歸因子在子樣本穩定性方面表現大幅優越：斜率R²在前後兩半期分別為+18.17%與+17.11%，而PCA方法則出現四倍的衰退。其三，統計可預測性對經濟價值的映射並不均勻斜率預測可產生獲利的風險逆轉策略（Sharpe > 1.0），而曲率預測則無法克服蝶式部位的時間值（Theta）衰減，顯示策略工具的成本結構是經濟可利用性的首要決定因素。方向性擇時策略的Sharpe比率最高達1.17，且在100個基點的交易成本下仍能存續。

This paper investigates the out-of-sample predictability of the implied volatility surface (IVS) for TAIFEX index options from 2007 to 2024. Utilizing 130 predictors across seven economic channels and seven machine learning models, we forecast monthly IVS factors—level, slope, and curvature—extracted via quadratic cross-sectional regressions following Collin-Dufresne et al. (2023). Our findings reveal a sharp asymmetry in predictability: while the level factor remains unpredictable, slope and curvature exhibit substantial and stable out-of-sample predictability. Specifically, Elastic Net achieves out-of-sample R^2 of +17.85% (slope) and +14.32% (curvature), maintaining positive rolling 36-month R^2 in nearly all windows. Feature importance analysis identifies lagged factor levels as dominant predictors driven by strong mean-reversion with incremental predictive power from futures open interest, macroeconomic policy rates, and regional geopolitical risk. This statistical predictability translates into highly profitable trading utilities. Direction-timing and risk-reversal strategies deliver annualized Sharpe ratios exceeding 1.0, even after accounting for transaction costs, with certainty-equivalent return gains reaching 500–1,050 basis points annually. Overall, this study demonstrates that ℓ₁ regularization substantially dominates ℓ₂ penalization in sparse IVS forecasting, and that quadratic factor extraction provides superior stability and economic interpretability compared to traditional PCA approaches.
Keywords: Implied Volatility Surface, Machine Learning, Out-of-Sample Forecasting, TAIFEX Options, Elastic Net, Variance Risk Premium, Geopolitical Risk

Baker, S.R., Bloom, N., & Davis, S.J. (2016). Measuring economic policy uncertainty. Quarterly Journal of Economics, 131(4), 1593–1636.
Bakshi, G., Cao, C., & Chen, Z. (1997). Empirical performance of alternative option pricing models. Journal of Finance, 52(5), 2003–2049.
Bates, D.S. (2000). Post-'87 crash fears in the S&P 500 futures options market. Journal of Econometrics, 94, 181–238.
Bernales, A. & Guidolin, M. (2014). Can we forecast the implied volatility surface dynamics of equity options? Journal of Banking & Finance, 46, 326–342.
Bianchi, D., Büchner, M., & Tamoni, A. (2021). Bond risk premiums with machine learning. Review of Financial Studies, 34(2), 1046–1089.
Black, F. (1976). Studies of stock price volatility changes. Proceedings of the 1976 ASA Meetings, 171–181.
Bollerslev, T., Tauchen, G., & Zhou, H. (2009). Expected stock returns and variance risk premia. Review of Financial Studies, 22(11), 4463–4492.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Caldara, D. & Iacoviello, M. (2022). Measuring geopolitical risk. American Economic Review, 112(4), 1194–1225.
Campbell, J.Y. & Thompson, S.B. (2008). Predicting excess stock returns out of sample. Review of Financial Studies, 21(4), 1509–1531.
Carr, P. & Wu, L. (2009). Variance risk premiums. Review of Financial Studies, 22(3), 1311–1341.
Chen, T. & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. KDD 2016, 785–794.
Christensen, B.J. & Prabhala, N.R. (1998). The relation between implied and realized volatility. Journal of Financial Economics, 50, 125–150.
Christie, A.A. (1982). The stochastic behavior of common stock variances. Journal of Financial Economics, 10(4), 407–432.
Christoffersen, P., Heston, S., & Jacobs, K. (2009). The shape and term structure of the index option smirk. Management Science, 55(12), 1914–1932.
Christoffersen, P., Fournier, M., & Jacobs, K. (2018). The factor structure in equity options. Review of Financial Studies, 31(2), 595–637.
Clark, T.E. & West, K.D. (2007). Approximately normal tests for equal predictive accuracy in nested models. Journal of Econometrics, 138(1), 291–311.
Collin-Dufresne, P., Goldstein, R.S., & Yang, F. (2023). How integrated are credit and equity markets? Evidence from index options. Journal of Finance, forthcoming.
Cont, R. & da Fonseca, J. (2002). Dynamics of implied volatility surfaces. Quantitative Finance, 2(1), 45–60.
Corsi, F. (2009). A simple approximate long-memory model of realized volatility. Journal of Financial Econometrics, 7(2), 174–196.
Diebold, F.X. & Li, C. (2006). Forecasting the term structure of government bond yields. Journal of Econometrics, 130(2), 337–364.
Diebold, F.X. & Mariano, R.S. (1995). Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3), 253–263.
Fengler, M.R., Härdle, W.K., & Mammen, E. (2007). A semiparametric factor model for implied volatility surface dynamics. Journal of Financial Econometrics, 5(2), 189–218.
Friedman, J.H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232.
Gonçalves, S. & Guidolin, M. (2006). Predictable dynamics in the S&P 500 index options implied volatility surface. Journal of Business, 79(3), 1591–1635.
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. Review of Financial Studies, 33(5), 2223–2273.
Harvey, C.R. & Whaley, R.E. (1992). Market volatility prediction and the efficiency of the S&P 100 index option market. Journal of Financial Economics, 31(1), 43–73.
Heston, S.L. (1993). A closed-form solution for options with stochastic volatility. Review of Financial Studies, 6(2), 327–343.
Hoerl, A.E. & Kennard, R.W. (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1), 55–67.
Jackwerth, J.C. (2000). Recovering risk aversion from option prices and realized returns. Review of Financial Studies, 13(2), 433–451.
Jiang, G.J. & Tian, Y.S. (2005). The model-free implied volatility and its information content. Review of Financial Studies, 18(4), 1305–1342.
Kozhan, R., Neuberger, A., & Schneider, P. (2013). The skew risk premium in the equity index market. Review of Financial Studies, 26(9), 2174–2203.
Litterman, R. & Scheinkman, J. (1991). Common factors affecting bond returns. Journal of Fixed Income, 1(1), 54–61.
Newey, W.K. & West, K.D. (1987). A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix. Econometrica, 55(3), 703–708.
Pan, J. & Poteshman, A.M. (2006). The information in option volume for future stock prices. Review of Financial Studies, 19(3), 871–908.
Rapach, D.E., Strauss, J.K., & Zhou, G. (2013). International stock return predictability. Journal of Finance, 68(4), 1633–1662.
Rapach, D.E. & Zhou, G. (2020). Time-series and cross-sectional stock return forecasting: New machine learning methods. In Machine Learning for Asset Management. Wiley.
Rubinstein, M. (1994). Implied binomial trees. Journal of Finance, 49(3), 771–818.
Skiadopoulos, G., Hodges, S., & Clewlow, L. (2000). The dynamics of the S&P 500 implied volatility surface. Review of Derivatives Research, 3(3), 263–282.
Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B, 58(1), 267–288.
Welch, I. & Goyal, A. (2008). A comprehensive look at the empirical performance of equity premium prediction. Review of Financial Studies, 21(4), 1455–1508.
Zou, H. & Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B, 67(2), 301–320.