AZAbdul Fahim Zeeshan

Abdul Fahim Zeeshan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Abdul Fahim Zeeshan has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Assessing the Effectiveness of Machine Learning Models in Predicting Stock Price Movements During Energy Crisis: Insights from Shell's Market Dynamics

    by Khalilor Rahman, Hossain Mohammad Dalim, Syed Ali Reza, Adib Ahmed, Abdul Fahim Zeeshan, Afrin Hoque Jui, Boktiar Nayeem

    The global energy crisis has presented an unprecedented degree of volatility and uncertainty in financial markets, specifically impacting the stock prices of energy sector organizations. Accurate forecasting of stock price patterns during such turbulent periods is essential for informed decision-making by investors, policymakers, and industry stakeholders. The main purpose of this study was to assess the effectiveness of different machine learning models in predicting stock price movements during an energy crisis. This research investigated the stock price fluctuations of Shell during the energy crisis, considering historical data and machine learning techniques to identify patterns and trends. The dataset for this study was sourced from accredited and credible sources providing a more detailed view of how the variation in stock prices of major energy firms was influenced by different energy crises that occurred during the period 2021-2024. The proposed three big energy companies listed under their abbreviations for convenience comprise ExxonMobil (XOM), Shelll-SHEL, and BP-BP; after which historical data was gathered using y-finance. This dataset was of great help to analysts interested in financial analysis, market behavior, and the impact of global events on the energy sector. The data consisted of the daily adjusted closing prices of the selected companies from January 2021 to date. Models like Logistic Regression, Random Forest classifiers, and Support Vector Machines classifiers were deployed since they offered distinct strengths and were capable of offering the right potential. The proven performance metric used encompassed Precision, Recall, Accuracy, and F1-Score. The Random Forest model has the highest accuracy at 0.52, followed by Logistic Regression with an accuracy of 0.51, and then the Support Vector Classifier with an accuracy of 0.50. There are great opportunities in the integration of machine learning and financial forecasting to improve predictive accuracy, especially in these volatile markets where prices fluctuate rapidly with immense uncertainty. Predictive models might also be put into practice by decision-makers within several finance-related spheres to great avail. In this regard, investment firms could practice machine learning for portfolio management by way of automated trading based on market signals in real-time. Predictive modeling of the energy crisis brings huge dividends for investors and analysts. The first among the main recommendations is to take advantage of the model predictions within a diversified investment strategy. In this direction, the investors must use the output of those different predictive models not as an isolated lead but as a complementary tool enhancing the traditional analysis techniques.


  • Predicting Energy Consumption in Hospitals Using Machine Learning: A Data-Driven Approach to Energy Efficiency in the USA

    by Adib Ahmed, Tanaya Jakir, Nazmul Hossain Mir, Abdul Fahim Zeeshan, Arat Hossain, Afrin Hoque Jui, Sakibul Hasan

    In the USA, hospitals are confronted with significant challenges regarding energy consumption, which not only impacts operational costs but also contributes to environmental concerns. The primary objective of this research was to develop and evaluate machine learning models that are capable of accurately predicting energy consumption in U.S. hospitals. This study will be focused on United States hospital energy consumption data, recognizing the unique difficulties and opportunities present in the U.S. healthcare setting. The data used for this hospital energy consumption analysis has been carefully gathered from multiple credible sources, including the U.S. Department of Energy's Energy Star program, whole-building hospital energy audits, and information from local utility providers. This variety in sourcing guarantees a strong and complete dataset that accurately represents real-world energy dynamics in healthcare buildings. In the model selection phase, three powerful algorithms were employed: the Random Forest Classifier, XG-Boost, and Artificial Neural Network (ANN). XG-Boost outperformed other models after tuning, achieving an 81.8% accuracy on the test set. Random Forest showed a decent improvement post-tuning but still lagged behind XG-Boost. Hospital managers can utilize machine learning (ML)--based predictions to achieve substantial cost savings in operational expenditures related to energy usage. With predictive analytics, hospitals can anticipate energy needs based on several parameters, such as patient occupancy rates, time of day, and seasonality. Integration of AI-driven energy prediction in hospital sustainability plans has significant policy implications for the U.S. healthcare sector. The integration of machine learning models and the Internet of Things (IoT)-)-)-enabled energy management systems is a breakthrough step in embracing smart hospital initiatives.