This project explores the use of multi-modal machine learning models to predict the likelihood of a successful deal on Avito, Russia’s largest classified advertisement platform. By integrating tabular, text, and image data, we demonstrate that ensemble learning and deep feature extraction significantly improve predictive performance. 
This Project explores the hypothesis that clustering stocks by time series similarity enhances the accuracy of the forecasting models. 
This Project examines optimization strategies to minimize ambulance response times in Manhattan: a min-sum model, a min-max model, and robust versions of both. The goal is to improve emergency medical services (EMS) efficiency while addressing equity and uncertainty challenges. Our approach integrates real-world constraints to provide actionable recommendations for dispatch optimization. 
Customer analysis is a vital component of any successful business strategy. By leveraging advanced data analysis techniques, we can gain a deeper understanding of our customers and tailor our products and operations to better meet their needs and preferences. In our project, we employ a range of analytical methods, including EDA, clustering, multiple linear regression, and machine learning for regression and classification. Through this analysis, we can gain valuable insights into the characteristics and spending behaviors of our customers. This information enables us to make informed decisions about marketing strategies and improve the overall success of the business. 
This project demonstrates that adaptive machine learning and reinforcement learning techniques offer superior ad targeting strategies, enabling businesses to reduce inefficient spending, improve engagement, and enhance marketing ROI in real-time digital advertising environments. 
We utilized Tableau and Python as tools to analyze and compare the stocks of two gaming companies, ATVI and EA. Our analysis involved various data exploration and visualization techniques, followed by the application of multiple models to fit and predict stock prices. Ultimately, we identified the characteristics of both stocks, compared their investment potential, and provided a recommendation, presenting our findings in a comprehensive report. 
As wind power plays an increasingly significant role in the energy structure, wind power prediction has become a prominent research topic. Accurate wind power forecasting can effectively guide peak shaving and energy storage management, promoting the utilization and development of wind energy. This study focuses on a given wind farm dataset, first conducting an exploratory analysis of the data and then employing both deep learning and statistical methods for ultra-short-term wind power forecasting. The primary focus is on evaluating the effectiveness of different neural network architectures in deep learning-based wind power prediction, providing deeper insights into the crucial role of big data and artificial intelligence in the energy and power sector. 
Soil organic carbon is an important component of the global carbon sink and plays a crucial role in maximizing soil carbon sequestration capacity and reducing soil respiration, thereby positively impacting carbon emission reduction. In line with sustainable development goals, Shanxi Province can achieve atmospheric carbon neutrality by limiting industrial carbon emissions and enhancing carbon sequestration technologies, such as promoting soil carbon sequestration. Understanding the spatiotemporal variations and future prospects of soil organic matter in Shanxi Province is significant for agricultural production and carbon sequestration in farmland. 