Optimizing Time Series Forecasting for AI Job Market Dynamics: A Comparative Study of SARIMA and Prophet with Cross-Validation
DOI:
https://doi.org/10.47738/ijiis.v9i2.296Keywords:
SARIMA, Prophet, AI Job Market, Time Series Forecasting, Model ComparisonAbstract
The rapid growth of Artificial Intelligence (AI) has led to significant shifts in the job market, making accurate forecasting essential for workforce planning and policy-making. This study aims to compare the effectiveness of two time series forecasting models, SARIMA and Prophet, in predicting AI job market trends. The primary focus was to evaluate their performance using RMSE and Time Series Cross-Validation (TSCV). The SARIMA model outperformed Prophet, particularly when capturing seasonal patterns, achieving an RMSE of 83.42, compared to Prophet's 136.01. The results demonstrate that SARIMA’s parameter tuning and seasonality handling contribute to more reliable forecasts, while Prophet’s flexibility offers advantages in non-linear data scenarios. The study provides valuable insights for stakeholders in adapting workforce strategies, particularly in AI-driven sectors, by recommending SARIMA for seasonal trends and Prophet for volatile, non-linear data.References
G. B. Isataeva, “Artificial Intelligence and the Transformation of Employment: A Systematic Literature Review,” Bull. Turan Univ., vol. 2025, no. 4, hal. 205–217, 2025, doi: 10.46914/1562-2959-2025-1-4-205-217.
A. Hassani dan M. Javadi, “Leveraging Artificial Intelligence to Study and Forecast Its Impacts on Employment Management and Wages in China’s Key Cities,” Spectr. Eng. Manag. Sci., vol. 4, no. 1, hal. 43–54, 2025, doi: 10.31181/sems41202660h.
F. Mahmud et al., “AI-Powered Workforce Analytics Forecasting Labor Market Trends and Skill Gaps for U.S. Economic Competitiveness,” J. Comput. Sci. Technol. Stud., vol. 6, no. 5, hal. 265–277, 2024, doi: 10.32996/jcsts.2024.6.5.21.
D. Liu, “Enterprise Digital Retail Business Data Analysis and Forecasting Based on Time Series Analysis,” Adv. Econ. Manag. Polit. Sci., vol. 77, no. 1, hal. 206–212, 2024, doi: 10.54254/2754-1169/77/20241678.
Fozia Sultana, Urooj Talpur, Muhammad Shahid Iqbal, Ahmed Ali, dan Khalid Hussain Memon, “The Macroeconomic Implications of Automation and AI on Labor Markets and Employment,” Crit. Rev. Soc. Sci. Stud., vol. 2, no. 2, hal. 497–507, Nov 2024, doi: 10.59075/f9hdkk61.
N. Masoud, “Artificial Intelligence and Unemployment Dynamics: An Econometric Analysis in High-Income Economies,” Technol. Sustain., vol. 4, no. 1, hal. 30–50, 2024, doi: 10.1108/techs-04-2024-0033.
W. Kao, “Impaction of Artificial Intelligence on the Labor Market,” Adv. Econ. Manag. Polit. Sci., vol. 84, no. 1, hal. 24–29, 2024, doi: 10.54254/2754-1169/84/20240772.
R. Jadhav dan A. Banubakode, “The Implications of Artificial Intelligence on the Employment Sector,” Int. J. Multidiscip. Res., vol. 6, no. 3, hal. 1–11, 2024, doi: 10.36948/ijfmr.2024.v06i03.22716.
R.-J. Yan, “The Impact of Artificial Intelligence on the Labor Market,” Int. J. Glob. Econ. Manag., vol. 2, no. 1, hal. 233–238, Jan 2024, doi: 10.62051/ijgem.v2n1.29.
R. Fu, “Analysis of the Effect of Artificial Intelligence on the Labor Market in the United States,” Adv. Econ. Manag. Polit. Sci., vol. 57, no. 1, hal. 78–84, 2024, doi: 10.54254/2754-1169/57/20230538.
E. Dahlin, “Who Says Artificial Intelligence Is Stealing Our Jobs?,” Socius Sociol. Res. a Dyn. World, vol. 10, no. 1, hal. 1–13, 2024, doi: 10.1177/23780231241259672.
R. Shengelia, “Artificial Intelligence and Labor Market Dynamics: Employment Problems and Development Trends,” Economics, vol. 107, no. 3–5, hal. 7–13, 2025, doi: 10.36962/ecs107/3-5/2025-07.
P. D. Nalwade, “Adapting to Tomorrow’s Workforce: Navigating the Impacts of Artificial Intelligence on Employment,” Interantional J. Sci. Res. Eng. Manag., vol. 08, no. 04, hal. 1–5, 2024, doi: 10.55041/ijsrem30664.
A. Havryk dan Т. Назарова, “Artificial Intelligence and Its Role in the Labor Market and Financial Sector Itself: US Point of View,” Int. Sci. J. Manag. Econ. Financ., vol. 3, no. 3, hal. 1–9, 2024, doi: 10.46299/j.isjmef.20240303.01.
Y. Zhao, “E-Commerce Demand Forecasting Using SARIMA Model and K-Means Clustering Analysis,” J. Innov. Dev., vol. 7, no. 1, hal. 1–6, 2024, doi: 10.54097/ctfb0379.
V. Arumugam dan V. Natarajan, “Time Series Modeling and Forecasting Using Autoregressive Integrated Moving Average and Seasonal Autoregressive Integrated Moving Average Models,” Instrum. Mes. Métrologie, vol. 22, no. 4, hal. 161–168, 2023, doi: 10.18280/i2m.220404.
M. Othman, R. Indawati, A. A. Suleiman, M. B. Qomaruddin, dan R. Sokkalingam, “Model Forecasting Development for Dengue Fever Incidence in Surabaya City Using Time Series Analysis,” Processes, vol. 10, no. 11, hal. 2454, 2022, doi: 10.3390/pr10112454.
G. Dudek, “STD: A Seasonal-Trend-Dispersion Decomposition of Time Series,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 10, hal. 10339–10350, Okt 2023, doi: 10.1109/TKDE.2023.3268125.
F. L. Aires, G. D. Galeno, F. N. Belchior, A. M. Oliveira, dan J. D. Hunt, “Enhancing three-phase induction motor reliability with health index and artificial intelligence-driven predictive maintenance,” R. Soc. Open Sci., vol. 12, no. 5, hal. 1–21, Mei 2025, doi: 10.1098/rsos.241946.
K. Albeladi, B. Zafar, dan A. Mueen, “A novel deep-learning based approach for time series forecasting using sarima, neural prophet and fb prophet,” Rev. Gestão Tecnol., vol. 24, no. Special, hal. 72–86, Mei 2024, doi: 10.20397/2177-6652/2024.v24iSpecial.2818.
G. V. S. A. Varma, G. V. N. A. Varma, dan A. Kethaan, “Predictive Insights for Monthly Property Sales Forecasting: An End-to-End Time Series Forecasting,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 3, no. 1, hal. 598–604, 2023, doi: 10.48175/ijarsct-12493.
S. Ryu, H. J. Nam, M. Jhon, J. Lee, J. Kim, dan S. Kim, “Trends in Suicide Deaths Before and After the COVID-19 Outbreak in Korea,” PLoS One, vol. 17, no. 9, hal. e0273637, 2022, doi: 10.1371/journal.pone.0273637.
Y. Shebalkova, J. K. Jacob, dan Y. Apanovych, “Silver and Palladium Price Dynamics: Analyzing Relationships and Forecasting with ARIMA and Prophet,” Acta Montan. Slovaca, vol. 30, no. 1, hal. 170–184, Jul 2025, doi: 10.46544/AMS.v30i1.13.
K. Karthick, S. Aruna, R. Shanmugasundaram, M. Safran, S. Alfarhood, dan W. Al-Rajhi, “Enhancing Sustainable Urban Energy Management Through Short-Term Wind Power Forecasting Using LSTM Neural Network,” Sustainability, vol. 15, no. 18, hal. 13424, 2023, doi: 10.3390/su151813424.
J. Tan, “NVIDIA Stock Price Prediction by Machine Learning,” Highlights Business, Econ. Manag., vol. 24, no. 1, hal. 1072–1076, Jan 2024, doi: 10.54097/dsz8ns50.
N. S. Wen dan L. S. Ling, “Evaluation of Cryptocurrency Price Prediction Using LSTM and CNNs Models,” JOIV Int. J. Informatics Vis., vol. 7, no. 3–2, hal. 2016, Nov 2023, doi: 10.30630/joiv.7.3-2.2344.
S. Kwarteng dan P. Andreevich, “Comparative Analysis of ARIMA, SARIMA and Prophet Model in Forecasting,” Res. Dev., vol. 5, no. 4, hal. 110–120, Okt 2024, doi: 10.11648/j.rd.20240504.13.
E. Spiliotis, F. Petropoulos, dan V. Assimakopoulos, “On the Disagreement of Forecasting Model Selection Criteria,” Forecasting, vol. 5, no. 2, hal. 487–498, 2023, doi: 10.3390/forecast5020027.
T. S. Talagala, R. J. Hyndman, dan G. Athanasopoulos, “Meta‐learning How to Forecast Time Series,” J. Forecast., vol. 42, no. 6, hal. 1476–1501, 2023, doi: 10.1002/for.2963.
F. Petropoulos dan E. Siemsen, “Forecast Selection and Representativeness,” Manage. Sci., vol. 69, no. 5, hal. 2672–2690, 2023, doi: 10.1287/mnsc.2022.4485.
A. Jakovljevic, L. Charlin, dan B. Barbeau, “Applying Recurrent Neural Networks and Blocked Cross-Validation to Model Conventional Drinking Water Treatment Processes,” Water, vol. 16, no. 7, hal. 1042, Apr 2024, doi: 10.3390/w16071042.
Downloads
Published
Issue
Section
License
Authors who publish with IJIIS : International Journal on Informatics and Information Systems agree to the following terms: Authors retain copyright and grant the IJIIS : International Journal on Informatics and Information Systems right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material) the work for any purpose, even commercially with an acknowledgement of the work's authorship and initial publication in IJIIS : International Journal on Informatics and Information Systems. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in IJIIS : International Journal on Informatics and Information Systems. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
