Time Series Analysis of FDI in India Using ARIMA-SVR Hybrid Machine Learning Model
Authors
-
M. Nagesh
Research Scholar, Department of Mathematics, GITAM Deemed to be University, Hyderabad - 502 329, Telangana
https://orcid.org/0009-0001-7886-8155
-
D. Mallikarjuna Reddy
Professor, Department of Mathematics, GITAM Deemed to be University, Hyderabad - 502 329, Telangana
https://orcid.org/0000-0002-6917-1401
-
Nitendra Kumar
Assistant Professor (Corresponding Author), Department of Decision Sciences, Amity Business School, Amity University, Noida - 201 303, Uttar Pradesh
https://orcid.org/0000-0001-7834-7926
-
Ravi Prakash Chaturvedi
Assistant Professor, Department of Computer Science and Applications, Sharda University, Greater Noida - 201 310, Uttar Pradesh
https://orcid.org/0000-0003-3216-5531
-
Annu Mishra
Assistant Professor, Department of Computer Science and Engineering, Sharda University, Greater Noida - 201 310, Uttar Pradesh
https://orcid.org/0000-0001-9442-0601
DOI:
https://doi.org/10.17010/ijf/2025/v19i9/175510Keywords:
foreign direct investment, autoregressive integrated moving average (ARIMA), support vector regression (SVM), hybrid machine learning, forecasting, economic implications.JEL Classification Codes : C22, C45, F21
Publication Chronology: Paper Submission Date : October 15, 2024 ; Paper sent back for Revision : April 20, 2025 ; Paper Acceptance Date : May 25, 2025 ; Paper Published Online : September 15, 2025
Abstract
Purpose : This research analyzed the temporal patterns of foreign direct investment (FDI) inflow in India for 53 years (1970–2023) to determine sectoral contributions and the general economic impact of FDI. The emphasis was on enhancing accuracy in time-series forecasting of the economic indicators employing sophisticated statistical and ML techniques.
Methodology : Annual FDI inflow data were modeled using three models: Autoregressive integrated moving average (ARIMA), support vector regression (SVR), and a hybrid ARIMA-SVR. ARIMA identified the linear trends, SVR fit the non-linearities, and the hybrid model combined both to take advantage of their complementary strengths. The performance was measured based on mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE).
Findings : The hybrid ARIMA-SVR model delivered better forecasting performance (MAE: 0.29114, MAPE: 21.8581, RMSE: 0.38378) compared to both ARIMA (MAE: 0.36215, MAPE: 28.76416, RMSE: 0.45884) and SVR (MAE: 0.34746, MAPE: 19.85233, RMSE: 0.46288).
Practical Implications : The results apprised the importance of hybrid modeling for decision makers, economists and analysts, in generating solid economic forecasts. The method could improve decision-making, policymaking, and investment policies through the delivery of accurate projections of economic trends.
Originality : This study was carried out through the application and comparison of ARIMA, SVR, and a hybrid ARIMA-SVR method for long-range FDI prediction in India. It showed the superiority of the hybrid model in combination with linear and non-linear dynamics, providing a methodology framework that can be applied to other economic time series.
Downloads
Published
How to Cite
Issue
Section
References
1) Agarwal, N., & Patavardhan, R. (2024). Indian social stock exchange as a funding avenue for social enterprises. Prabandhan: Indian Journal of Management, 17(7), 42–56. https://doi.org/10.17010/pijom/2024/v17i7/173636 DOI: https://doi.org/10.17010/pijom/2024/v17i7/173636
2) 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 DOI: https://doi.org/10.17010/ijf/2022/v16i9/172157
3) 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 DOI: https://doi.org/10.17010/ijf/2021/v15i8/165817
4) Arifin, S., Manurung, M. M., Jonathan, S., Effendi, M., & Prasetyo, P. W. (2024). Trend analysis of the ARIMA method: A survey of scholarly works. Recent in Engineering Science and Technology, 2(3), 1–14. https://www.mbi-journals.com/index.php/riestech/article/view/65
5) Arodoye, N. L., & Abusomwan, S. O. (2022). Fiscal decentralization and the efficiency of public service delivery. Arthshastra Indian Journal of Economics & Research, 11(1), 8–23. https://doi.org/10.17010/aijer/2022/v11i1/169676 DOI: https://doi.org/10.17010/aijer/2022/v11i1/169676
6) Awariefe, C., & Ogbereyivwe, O. (2025). Time series modelling and forecasting foreign direct investment using linear and nonlinear models: The case of Nigeria. Journal of Basics and Applied Sciences Research, 2(1), 46–53. https://doi.org/10.33003/jobasr-2024-v2i1-33 DOI: https://doi.org/10.33003/jobasr-2024-v2i1-33
7) Banik, D., & Shil, S. (2023). FDI: A robust and easily accessible approach in fostering the achievement of Sustainable Development Goals 2030 in India – A perspective study. International Journal of Advanced Research in Science, Communication and Technology, 3(1), 104–110. https://doi.org/10.48175/IJARSCT-13114 DOI: https://doi.org/10.48175/IJARSCT-13114
8) Barua, P., Mahapatra, S., Rautaray, S. S., & Pandey, M. (2021). Analysis of FDIs in different sectors of the Indian economy. In Machine learning: Theoretical foundations and practical applications (pp. 137–153). Springer. https://doi.org/10.1007/978-981-33-6518-6_8 DOI: https://doi.org/10.1007/978-981-33-6518-6_8
9) Basumatary, J. (2022). Effects of tax revenue and capital expenditure on economic growth: A case study of the Union Territory of Puducherry, India. Arthshastra Indian Journal of Economics & Research, 11(2), 8–21. https://doi.org/10.17010/aijer/2022/v11i2/172209 DOI: https://doi.org/10.17010/aijer/2022/v11i2/172209
10) Boozary, P., Sheykhan, S., & GhorbanTanhaei, H. (2025). Forecasting the Bitcoin price using various machine learning techniques: A systematic review in data-driven marketing. Systems and Soft Computing, 7, Article ID 200209. https://doi.org/10.1016/j.sasc.2025.200209 DOI: https://doi.org/10.1016/j.sasc.2025.200209
11) Chen, G., & Jia, G. (2024). A hybrid causal machine learning to reveal driving factors responsible coal market: Case of the Chinese industry. Journal of Cleaner Production, 434, Article ID 140249. https://doi.org/10.1016/j.jclepro.2023.140249 DOI: https://doi.org/10.1016/j.jclepro.2023.140249
12) Chhina, A. P. (2023). Regional distribution of foreign direct investment in India. Regional Economic Development Research, 4(2), 67–82. https://doi.org/10.37256/redr.4220232694 DOI: https://doi.org/10.37256/redr.4220232694
13) Chrystella, D. F., Ibrahim, S., & Lihua, Y. (2025). Maximizing the impact of foreign direct investment: Trends, determinants, and strategies for sustainable economic and social development. IOSR Journal of Economics and Finance, 16(1), 31–50. https://doi.org/10.9790/5933-1601043150 DOI: https://doi.org/10.9790/5933-1601043150
14) Divakar, V., & Dhilipan, C. (2024). FDI in India: Analyzing financial flows and economic impacts. International Journal of Scientific Research in Engineering and Management, 8(4), 1–18. https://doi.org/10.55041/IJSREM30482 DOI: https://doi.org/10.55041/IJSREM30482
15) Dobrina, M. V. (2024). ARIMA model in machine learning: Time series prediction. Soft Measurements and Computing, 1(74), 36–47. https://doi.org/10.36871/2618-9976.2024.01.004 DOI: https://doi.org/10.36871/2618-9976.2024.01.004
16) Garg, H., & Singh, S. (2025). Cross-border dynamics: Analyzing exchange rates' impact on Indian underlying stocks and ADRs. Arthshastra Indian Journal of Economics & Research, 14(1), 82–97. https://doi.org/10.17010/aijer/2025/v14i1/174337 DOI: https://doi.org/10.17010/aijer/2025/v14i1/174337
17) Gupta, V. (2024a). Corporate governance and credit risk: Evidence on Indian firms using a mixed-method approach. Prabandhan: Indian Journal of Management, 17(7), 8–22. https://doi.org/10.17010/pijom/2024/v17i7/173633 DOI: https://doi.org/10.17010/pijom/2024/v17i7/173633
18) Gupta, S. (2024b). Foreign direct investment and its impact on India's economic growth. Innovative Research Thoughts, 10(3), 111–122. https://doi.org/10.36676/irt.v10.i3.1469 DOI: https://doi.org/10.36676/irt.v10.i3.1469
19) Guru, S., & Panda, P. (2024). Financial sustainability: The influence of internal efficiency in Indian commercial banks. Prabandhan: Indian Journal of Management, 17(10), 37–55. https://doi.org/10.17010/pijom/2024/v17i10/173995 DOI: https://doi.org/10.17010/pijom/2024/v17i10/173995
20) Islam, M. M., Jannat, A., Aruga, K., & Rashid, M. M. (2024). Forecasting foreign direct investment inflow to Bangladesh: Using an autoregressive integrated moving average and a machine learning-based random forest approach. Journal of Risk and Financial Management, 17(10), 451. https://doi.org/10.3390/jrfm17100451 DOI: https://doi.org/10.3390/jrfm17100451
21) Jianchun, F., & Yuhua, S. (2011). Notice of retraction: The new trends and impacts of the development of foreign direct investment. In 2011 International Conference on E-Business and E-Government (ICEE) (pp. 1–6). IEEE. https://doi.org/10.1109/ICEBEG.2011.5882256 DOI: https://doi.org/10.1109/ICEBEG.2011.5882256
22) Kemiveš, A., Ranđelović, M., Barjaktarović, L., Đikanović, P., Čabarkapa, M., & Ranđelović, D. (2024). Identifying key indicators for successful foreign direct investment through asymmetric optimization using machine learning. Symmetry, 16(10), 1346. https://doi.org/10.3390/sym16101346 DOI: https://doi.org/10.3390/sym16101346
23) Khanna, S., & Kumar, A. (2020). GARCH and TGARCH approach to information linkages. Indian Journal of Finance, 14(8–9), 35–51. https://doi.org/10.17010/ijf/2020/v14i8-9/154947 DOI: https://doi.org/10.17010/ijf/2020/v14i8-9/154947
24) Kothadia, K. D., & Nayak, D. N. (2020). Modeling inflation in India: A univariate approach. Arthshastra Indian Journal of Economics & Research, 9(2–3), 25–38. https://doi.org/10.17010/aijer/2020/v9i2-3/155602 DOI: https://doi.org/10.17010/aijer/2020/v9i2-3/155602
25) Kumar, P., Kaur, H., & Singh, G. (2023). MSMEs in emerging markets: An exploration of the stage model of e-commerce adoption. Prabandhan: Indian Journal of Management, 16(8), 8–23. https://doi.org/10.17010/pijom/2023/v16i8/173062 DOI: https://doi.org/10.17010/pijom/2023/v16i8/173062
26) Kumar, R., & Neogi, D. (2025). Strategic economic management: ARDL analysis of trade, FDI, and growth in G20 nations. Prabandhan: Indian Journal of Management, 18(7), 8–25. https://doi.org/10.17010/pijom/2025/v18i7/174562 DOI: https://doi.org/10.17010/pijom/2025/v18i7/174562
27) Kumar, R., & Singh, S. (2023). A study of foreign direct investment in the Indian insurance industry. International Journal of Foreign Trade and International Business, 5(1_Part A), 31–35. https://doi.org/10.33545/26633140.2023.v5.i1a.85 DOI: https://doi.org/10.33545/26633140.2023.v5.i1a.85
28) Magazzino, C., & Mele, M. (2022). Can a change in FDI accelerate GDP growth? Time-series and ANNs evidence on Malta. The Journal of Economic Asymmetries, 25, Article ID e00243. https://doi.org/10.1016/j.jeca.2022.e00243 DOI: https://doi.org/10.1016/j.jeca.2022.e00243
29) Menéndez-García, L. A., García-Nieto, P. J., García-Gonzalo, E., & Sánchez Lasheras, F. (2024). Time series analysis for COMEX platinum spot price forecasting using SVM, MARS, MLP, VARMA and ARIMA models: A case study. Resources Policy, 95, Article ID 105148. https://doi.org/10.1016/j.resourpol.2024.105148 DOI: https://doi.org/10.1016/j.resourpol.2024.105148
30) Mohapatra, A. K., Das, R. C., & Khilar, S. (2025). Financial inclusion and socio-economic development: The mediating role of social empowerment in rural Odisha of India. Indian Journal of Finance, 19(6), 29–45. https://doi.org/10.17010/ijf/2025/v19i6/175130 DOI: https://doi.org/10.17010/ijf/2025/v19i6/175130
31) Muthukamu, M., & Amudha, R. (2020). The rollout of GST and its impact on the auto sector stocks of National Stock Exchange. Indian Journal of Finance, 14(12), 25–39. https://doi.org/10.17010/ijf/2020/v14i12/156482 DOI: https://doi.org/10.17010/ijf/2020/v14i12/156482
32) Nabil, M. (2024). The impact of foreign direct investments on the performance of Egyptian stock market sectors using machine learning techniques. International Journal of Economics and Finance, 16(10), 92–100. https://doi.org/10.5539/ijef.v16n10p92 DOI: https://doi.org/10.5539/ijef.v16n10p92
33) Nagesh, M., Reddy, D. M., Kumar, N., & Tripathi, P. (2025). Predicting FMCG indexes using ARIMA, SVM and ARIMA–SVM hybrid forecasting models. Journal of Information Systems Engineering and Management, 10(21s), 570–577. https://doi.org/10.52783/jisem.v10i21s.3394 DOI: https://doi.org/10.52783/jisem.v10i21s.3394
34) Nayak, D., & Barodawala, R. (2021). The impact of macroeconomic factors on the Indian stock market: An assessment. Arthshastra Indian Journal of Economics & Research, 10(2–3), 27–40. https://doi.org/10.17010/aijer/2021/v10i2-3/167172 DOI: https://doi.org/10.17010/aijer/2021/v10i2-3/167172
35) Nazareth, N., & Reddy, Y. V. (2023). Financial applications of machine learning: A literature review. Expert Systems with Applications, 219, Article ID 119640. https://doi.org/10.1016/j.eswa.2023.119640 DOI: https://doi.org/10.1016/j.eswa.2023.119640
36) Panackal, N., Rautela, S., & Sharma, A. (2024). Hypothesizing the enablers of the gig economy: A TISM and MICMAC approach. Prabandhan: Indian Journal of Management, 17(7), 23–41. https://doi.org/10.17010/pijom/2024/v17i7/173635 DOI: https://doi.org/10.17010/pijom/2024/v17i7/173635
37) 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 DOI: https://doi.org/10.17010/ijf/2022/v16i10/172385
38) Routray, M., Jha, U. K., & Giri, A. (2025). Consumer acceptance of green fuel in Indian retail fuel outlets: Developing a conceptual model using behavioral reasoning theory (BRT). Prabandhan: Indian Journal of Management, 18(1), 63–71. https://doi.org/10.17010/pijom/2025/v18i1/174108 DOI: https://doi.org/10.17010/pijom/2025/v18i1/174108
39) Salunkhe, V. J., & Kashyap, S. K. (2024). Trends in industry sectors and geographic locations attracting maximum outward FDI from India. Panamerican Mathematical Journal, 34(4), 331–348. https://doi.org/10.52783/pmj.v34.i4.2030 DOI: https://doi.org/10.52783/pmj.v34.i4.2030
40) Sathvik, S. (2024). Is foreign direct investment- A new engine for growth and economic development of India? BSSS Journal of Commerce, 16(1), 173–184. https://doi.org/10.51767/joc1613 DOI: https://doi.org/10.51767/joc1613
41) 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 DOI: https://doi.org/10.17010/ijf/2021/v15i8/165816
42) Shah, F. A., & Hussain, S. (2024). Impact of crisis management strategies on destination market recovery. Prabandhan: Indian Journal of Management, 17(2), 8–23. https://doi.org/10.17010/pijom/2024/v17i2/173326 DOI: https://doi.org/10.17010/pijom/2024/v17i2/173326
43) Singh, R. K., Verma, V. K., Kumar, N., Agarwal, P., & Tiwari, S. (2023). Time series forecasting of stock price of AirAsia Berhad using ARIMA model during COVID-19. Journal of Statistics and Management Systems, 26(6), 1421–1429. https://doi.org/10.47974/JSMS-1189 DOI: https://doi.org/10.47974/JSMS-1189
44) Singh, S., & Hoque, D. (2024). An analysis of trend, pattern and strength of foreign direct investment (FDI) and foreign institutional investment (FII) to India. Educational Administration: Theory and Practice, 30(4), 3588–3594. https://doi.org/10.53555/kuey.v30i4.2083 DOI: https://doi.org/10.53555/kuey.v30i2.1699
45) Soni, N., & Kumar, M. (2024). The dynamics of FPI and FDI in the Indian economy: A correlational study. International Journal for Multidisciplinary Research, 6(6), 305–312. https://doi.org/10.36948/ijfmr.2024.v06i06.30552 DOI: https://doi.org/10.36948/ijfmr.2024.v06i06.30552
46) 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 DOI: https://doi.org/10.17010/ijf/2021/v15i12/167306
47) Thakkar, P. (2024). FDI in India: An analysis of legal frameworks and investor protections. International Education and Research Journal, 10(7), 57–61. https://doi.org/10.21276/IERJ24528308738806 DOI: https://doi.org/10.21276/IERJ24528308738806
48) Venkatachalam, A., & Nalini, G. S. (2022). Valuation of top three FMCG companies in India. Indian Journal of Finance, 16(7), 57–70. https://doi.org/10.17010/ijf/2022/v16i7/170654 DOI: https://doi.org/10.17010/ijf/2022/v16i7/170654
49) World Bank Group. (n.d.). Foreign direct investment, net inflows (% of GDP) – India. World Development Indicators. https://data.worldbank.org/indicator/BX.KLT.DINV.WD.GD.ZS?locations=IN
