Abstract: After years of trial and error in the oil and petrochemical industry, no clear consensus has been reached on which big data algorithms are most suitable for the specific characteristics of the sector's data. Repeated trial-and-error approaches have dispersed human and material resources and hindered the progress of intelligent development. Based on international and domestic literature databases, 87 highly relevant articles were collected from over 800 publications related to big data applications in the oil and petrochemical sector over the past decade. These articles were categorized according to their content and keywords into three groups: exploration and development (47 articles), oil and gas storage and transportation (25 articles), and petrochemical processes (15 articles). Using the ARIMA model, the fitted equation, with a goodness-of-fit exceeding 0.8, indicates that it can be used to predict the development trends of big data algorithms in the oil and petrochemical field over the next five years. Additionally, the average number of algorithm application frequency was used as a benchmark; algorithms with publication counts above this average were deemed more likely to be suitable for the sector’s data characteristics. Over the next five years, the number of algorithms applied to solve specific problems in the oil and petrochemical sector is projected to decrease from 25 to 9. In the exploration and development category, the number of algorithms is expected to reduce from 24 to 5. In the oil and gas storage and transportation category, the number is anticipated to decline from 19 to 6. For the petrochemical category, the number of algorithms is predicted to decrease from 13 to 4. The time series prediction of the future development trends of big data algorithms in the oil and petrochemical industry has revealed the trajectory of big data technology development and research gaps in this field. These findings provide valuable insights for choosing research project directions in the oil and petrochemical industry.