Stock market prediction is a critical area of financial research that aims to forecast future price movements of stocks using historical data, economic indicators, and advanced machine learning algorithms. This thesis focuses on utilizing the dataset titled "Stock Market Prediction & Forecasting" from Kaggle to develop predictive models capable of generating accurate market forecasts. The study investigates various methodologies, including time series analysis, feature engineering, and the application of machine learning techniques such as Random Forest, XGBoost, and Long Short-Term Memory (LSTM) networks. Results demonstrate the feasibility of achieving meaningful insights into stock price trends, enabling investors and analysts to make informed decisions.
As global energy demands soar, understanding and accurately forecasting energy consumption becomes crucial for both economic stability and sustainable development. This paper explores the application of machine learning techniques to predict energy consumption, using the "World Energy Consumption" dataset from Kaggle. Focusing on Kyrgyzstan as a case study, we investigate how factors such as energy per capita, population, and GDP influence energy demand. Employing a regression model, we evaluate the effectiveness of socioeconomic indicators in predicting energy needs. Results demonstrate the potential for these methods to contribute to energy management strategies, though limitations point toward the need for more complex models and broader datasets.
The goal of this research is to analyze model of electric power consumption of Kyrgyzstan and to build a data-driven model to predict the consumption for the future. Using historical electricity consumption data from World Bank, in the present study, modern machine learning approaches are used in order to provide accurate and interpretable predictions. The primary aim is to help policy makers and energy planners to identify models which are able to capture underlying consumption drivers. These results validate the use of machine learning models over traditional statistical models for better predictive performance and importance in national energy planning. This thesis adds to the emerging literature on energy forecasting in developing countries by offering a case study based on local data and policy.
Dynamic power reduction in SRAM (Static Random Access Memory) is essential for improving energy efficiency in modern digital systems, especially in processors and embedded devices. As SRAM power consumption contributes significantly to overall chip power, optimizing power in SRAM is critical. This thesis explores recent techniques for dynamic power reduction in SRAM, with a focus on architectural modifications, dynamic voltage scaling, adaptive voltage supply, and optimized circuit designs. This abstract outlines the need for low-power SRAM in reducing heat, noise, and electro-migration, particularly in high-performance computing. The research highlights how Multi-Tree Voltage Regulator (MTR) techniques and other dynamic power management methods contribute to significant reductions in power and heat generation, thereby enhancing both performance and reliability.