Purpose : The study examined whether commodity prices and institutional investment flows improved out-of-sample forecasts of monthly returns on the benchmark index of the National Stock Exchange of India, and whether classical econometric models differed from machine learning and deep learning models in forecasting accuracy.

Design/Methodology/Approach : Monthly observations from April 2000 to March 2026 on gold, silver, and crude oil prices and on net foreign and domestic institutional investment flows were analyzed under a chronological, leakage-controlled design. The autoregressive integrated moving average and vector autoregression benchmarks were compared with Gaussian process regression, a long short-term memory network, and hybrid residual models, with predictor ablation across 10 random seeds.

Findings : No model improved on the random walk benchmark; no model achieved a positive out-of-sample R² on returns, and directional accuracy did not differ significantly from chance. No difference that was nominally significant before correction remained significant after Holm-Bonferroni adjustment for multiple testing. The apparent hybrid gains disappeared once the base model was correctly specified on returns, because its residuals were then serially uncorrelated and left no structure for the residual models to extract.

Practical Implications : Commodity prices and institutional flows offered practitioners no monthly forecasting advantage for the NSE index and increased estimation instability. The study recommended three reporting practices: base-model residual diagnostics before any hybrid gain is claimed, dispersion across random-seed replicates, and R² computed on returns rather than on index levels.

Originality/Value : The study evaluated commodity and institutional-flow predictors of Indian index returns out of sample. Classical, deep learning, machine learning, and hybrid models were evaluated by means of a single method: strict time series partitioning with control over data leakage. We examined residual diagnostics, variation across random seeds, and multiple testing controls. The findings indicated that improvements attributed to hybrid models might be due to an inadequately defined base model rather than statistical and deep learning elements truly working together.

1)  Agarwal, S. (2022). Deep learning in financial analytics: Exchange rate modelling. Indian Journal of Finance, 16(9), 8–25. https://doi.org/10.17010/ijf/2022/v16i9/172157

2)  Agrawal, P. K., Nandan, T., & Singh, A. P. (2021). Integration of the Indian stock market with select Asian stock markets: An analysis. Indian Journal of Finance, 15(8), 40–51. https://doi.org/10.17010/ijf/2021/v15i8/165817

3)  Al-Najjar, D. M. (2016). Modelling and estimation of volatility using ARCH/GARCH models in Jordan's stock market. Asian Journal of Finance & Accounting, 8(1), 152–167. https://doi.org/10.5296/ajfa.v8i1.9129

4)  Ashraf, S., & Baig, M. A. (2019). Is the Indian stock market efficiently inefficient? An empirical investigation. Indian Journal of Finance, 13(7), 7–28. https://doi.org/10.17010/ijf/2019/v13i7/145532

5)  Aziz, T., Sadhwani, R., Habibah, U., & Al Janabi, M. A. M. (2020). Volatility spillover among equity and commodity markets. Sage Open, 10(2). https://doi.org/10.1177/2158244020924418

6)  Basak, S., & Pavlova, A. (2016). A model of financialization of commodities. The Journal of Finance, 71(4), 1511–1556. https://doi.org/10.1111/jofi.12408

7)  Dadhich, G., Chotia, V., & Chaudhry, O. (2015). Impact of foreign institutional investments on stock market volatility in India. Indian Journal of Finance, 9(10), 22–35. https://doi.org/10.17010/ijf/2015/v9i10/79561

8)  Danak, D., & Patel, N. (2020). A study of efficiency of index futures, lead-lag relationship, and speed of adjustments in India using high-frequency data. Indian Journal of Finance, 14(4), 7–23. https://doi.org/10.17010/ijf/2020/v14i4/151705

9)  De, S., & Ghosh, K. D. (2019). Mutual fund and foreign institutional investors: Pre and post crisis dynamics. Indian Journal of Research in Capital Markets, 6(2), 7–19. https://doi.org/10.17010/ijrcm/2019/v6/i2/146591

10)  Dikshita, & Singh, H. (2019). Estimating and forecasting volatility using ARIMA model: A study on NSE, India. Indian Journal of Finance, 13(5), 37–51. https://doi.org/10.17010/ijf/2019/v13i5/144184

11)  Fry-McKibbin, R., & McKinnon, K. (2023). The evolution of commodity market financialization: Implications for portfolio diversification. Journal of Commodity Markets, 32, Article 100360. https://doi.org/10.1016/j.jcomm.2023.100360

12)  Goldstein, I., & Yang, L. (2022). Commodity financialization and information transmission. The Journal of Finance, 77(5), 2613–2667. https://doi.org/10.1111/jofi.13165

13)  Gupta, N., Sachdeva, J. K., & Mishra, A. K. (2024). War-induced energy commodity price dynamics: Index design and impact assessment. Indian Journal of Finance, 18(10), 8–23. https://doi.org/10.17010/ijf/2024/v18i10/174611

14)  Huang, J., Chen, B., Xu, Y., & Xia, X. (2023). Time-frequency volatility transmission among energy commodities and financial markets during the COVID-19 pandemic: A novel TVP-VAR frequency connectedness approach. Finance Research Letters, 53, Article 103634. https://doi.org/10.1016/j.frl.2023.103634

15)  Iqbal, & Mallikarjunappa, T. (2010). A study of efficiency of the Indian stock market. Indian Journal of Finance, 4(5), 32–38. https://www.indianjournaloffinance.co.in/article/a-study-of-efficiency-of-the-indian-stock-market/

16)  Jain, S., Puri, N., & Rabbani, M. R. (2025). Dynamic interconnectedness and risk transmission in green, clean energy, and sustainable markets. Indian Journal of Finance, 19(12), 29–48. https://doi.org/10.17010/ijf/2025/v19i12/175876

17)  Kaura, R., Kishor, N., & Rajput, N. (2019). Arbitrage, error correction, and causality: Case of highly traded agricultural commodities in India. Indian Journal of Finance, 13(9), 7–21. https://doi.org/10.17010/ijf/2019/v13i9/147095

18)  Kumar, N., & Goel, D. (2024). Macroeconomic determinants of price dynamics in the Indian stock market. Indian Journal of Finance, 18(9), 25–41. https://doi.org/10.17010/ijf/2024/v18i9/174457

19)  Lai, F., Wu, Q., Xiong, D., & Zhu, S. (2024). How foreign institutional investors' ownership affects stock liquidity? Evidence from China. Sage Open, 14(2). https://doi.org/10.1177/21582440241260509

20)  Lethesh, M., & Viswanatha Reddy, C. (2023). Price discovery mechanism in the Indian agricultural commodity futures market: An empirical analysis. Indian Journal of Finance, 17(12), 8–25. https://doi.org/10.17010/ijf/2023/v17i12/172823

21)  Lu, R., Xu, W., Zeng, H., & Zhou, X. (2023). Volatility connectedness among the Indian equity and major commodity markets under the COVID-19 scenario. Economic Analysis and Policy, 78, 1465–1481. https://doi.org/10.1016/j.eap.2023.05.020

22)  Mishra, A. (2019). Foreign exchange, gold, and real estate markets in India: An analysis of return volatility and transmission. Indian Journal of Finance, 13(7), 50–64. https://doi.org/10.17010/ijf/2019/v13i7/145535

23)  Mohapatra, A. K., Mohanty, D., Sardana, V., & Shrivastava, A. (2024). The ripple effect: Influence of exchange rate volatility on Indian sectoral indices. Indian Journal of Finance, 18(2), 8–24. https://doi.org/10.17010/ijf/2024/v18i2/173519

24)  Nagesh, M., Reddy, D. M., Kumar, N., Chaturvedi, R. P., & Mishra, A. (2025). Time series analysis of FDI in India using ARIMA-SVR hybrid machine learning model. Indian Journal of Finance, 19(9), 73–88. https://doi.org/10.17010/ijf/2025/v19i9/175510

25)  Nagina, R. (2022). The nexus of stock markets among BRICS nations: An empirical analysis pre and post spread of the COVID-19 pandemic. Indian Journal of Finance, 16(10), 24–42. https://doi.org/10.17010/ijf/2022/v16i10/172386

26)  Parthasarathy, S. (2019). Revisiting the weak form efficiency with structural breaks: Evidence from the Indian stock market. Indian Journal of Finance, 13(10), 7–21. https://doi.org/10.17010/ijf/2019/v13i10/147744

27)  Petrozziello, A., Troiano, L., Serra, A., Jordanov, I., Storti, G., Tagliaferri, R., & La Rocca, M. (2022). Deep learning for volatility forecasting in asset management. Soft Computing, 26(17), 8553–8574. https://doi.org/10.1007/s00500-022-07161-1

28)  Pinto-Ávalos, F., Bowe, M., & Hyde, S. (2024). Revisiting the pricing impact of commodity market spillovers on equity markets. Journal of Commodity Markets, 33, Article 100369. https://doi.org/10.1016/j.jcomm.2023.100369

29)  Rai, S. K., & Sharma, A. K. (2022). Do lagged terms affect exchange rate volatility in India? An analysis using ARIMA model. Indian Journal of Finance, 16(10), 8–23. https://doi.org/10.17010/ijf/2022/v16i10/172385

30)  Rossi, B. (2012). The changing relationship between commodity prices and equity prices in commodity exporting countries. IMF Economic Review, 60(4), 533–569. https://doi.org/10.1057/imfer.2012.20

31)  Sakthivel, P., Bodkhe, N., & Kamaiah, B. (2012). Correlation and volatility transmission across international stock markets: A bivariate GARCH analysis. International Journal of Economics and Finance, 4(3), 253–264. https://doi.org/10.5539/ijef.v4n3p253

32)  Satapathy, A. (2026). Validity of arbitrage pricing theory (APT) and its comparison with CAPM. Indian Journal of Finance, 20(4), 27–41. https://doi.org/10.17010/ijf/2026/v20i4/175440

33)  Sathish, P. (2020). An analysis of trading behaviour of foreign and domestic institutional investors in the Indian stock market: An empirical study. Indian Journal of Research in Capital Markets, 7(1), 22–37. https://doi.org/10.17010/ijrcm/2020/v7i1/153629

34)  Seth, N., & Sidhu, A. (2021). Price discovery and volatility spillover for Indian energy futures market in the pre- and post-crisis periods. Indian Journal of Finance, 15(8), 24–39. https://doi.org/10.17010/ijf/2021/v15i8/165816

35)  Singh, R. K., Sharma, T., Singh, Y., Kumar, A., & Kumar, S. (2025). Modeling asymmetric volatility connectedness and spillover dynamics in emerging forex markets through the lens of a TVP-VAR framework. Indian Journal of Finance, 19(10), 8–38. https://doi.org/10.17010/ijf/2025/v19i10/175677

36)  Singhal, R., Gupta, P., & Singh, A. (2023). Identifying performance indicators for the agriculture sector in developing countries through the ARDL model: Special reference of India. Indian Journal of Finance, 17(2), 68–81. https://doi.org/10.17010/ijf/2023/v17i2/170145

37)  Sonia, & Narwal, K. P. (2023). Volatility spillover in the Indian commodity market: A comparative assessment of various commodity segments. Indian Journal of Finance, 17(2), 54–67. https://doi.org/10.17010/ijf/2023/v17i2/169193

38)  Suphawan, K., Kardkasem, R., & Chaisee, K. (2022). A Gaussian process regression model for forecasting Stock Exchange of Thailand. Trends in Sciences, 19(6), Article 3045. https://doi.org/10.48048/tis.2022.3045

39)  Syed, A. A., Tripathi, R., & Deewan, J. (2021). Investigating the impact of the first and second waves of the COVID-19 pandemic on the Indian stock and commodity markets: An ARDL analysis of gold, oil, and stock market prices. Indian Journal of Finance, 15(12), 8–21. https://doi.org/10.17010/ijf/2021/v15i12/167306

40)  Tariyal, P. (2017). A study on intersectoral linkages in Indian economy. Arthshastra Indian Journal of Economics & Research, 6(1), 23–34. https://doi.org/10.17010/aijer/2017/v6i1/111020

41)  Thouseef Ahamed, G., Tallapalli, N. K., Akula, P., & Shyam Kumar, K. (2026). Global commodities and the Indian stock market: A post-pandemic volatility spillover analysis. Indian Journal of Finance, 20(2), 8–25. https://doi.org/10.17010/ijf/2026/v20i2/175359

42)  Vaishnavi, D., Santosh, B. R., & Desai, G. (2026). Geopolitical risk forecasting for Indian agricultural commodity markets. Indian Journal of Finance, 20(7), 44–63. https://doi.org/10.17010/ijf/2026/v20i7/176066

43)  Varughese, A., & Mathew, T. (2017). Asymmetric volatility of the Indian stock market and foreign portfolio investments: An empirical study. Indian Journal of Finance, 11(6), 36–49. https://doi.org/10.17010/ijf/2017/v11i6/115595

44)  Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159–175. https://doi.org/10.1016/S0925-2312(01)00702-0