Forecasting Stock Prices: A Machine Learning-Based Approach for Predictive Analytics Through a Case Study

Stock price prediction has always been a challenging task, requiring careful observation of trends and dynamics of the market because of the volatile and complex nature of financial markets. Various factors affect market behavior all the time. Even some unquantifiable factors like 25 Oct 2025 (Published Online) emotions of the masses, social and political dynamics, etc., also play a great role. So perfect Machine Learning, Deep Learning, behaviors into consideration is crucial for better prediction of the ups and downs of prices. SMA, EMA, RSI, MACD, Bollinger Various machine learning and deep learning models have been proposed to tackle the challenges Bands, RFE, Random Forest by capturing and interpreting complex patterns and relationships in historical price data. Regressor, Multivariate Analysis, Technical features are important for understanding market trends and thus improving the LSTM. accuracy of stock price predictions. In this paper, we calculate key technical indicators such as Simple Moving Average (SMA), Exponential Moving Average (EMA), Relative Strength Index (RSI), Moving Average Convergence Divergence (MACD), Bollinger Bands, and others. We then focus on selecting the most relevant indicators by employing feature selection methods from these to enhance the extraction of meaningful features reflecting underlying market behavior and increase the probability of more precise prediction. Here, Recursive Feature Elimination (RFE) and Random Forest Regressor-based importance ranking methods have been applied for the feature selection task. To get a better forecast of market price, it is important to capture long- term dependencies and patterns over time. Long Short-Term Memory (LSTM) networks are well- suited for modeling and predicting sequential data like stock prices. By leveraging an LSTM model and taking the selected features, we do a multivariate analysis to forecast stock price based on historical data, identifying the trends fairly accurately with some lags here and there.

Digital Transformation in Business: Strategies and Implications for Organizational Change

By MD Ahsan Ullah Imran

Advanced algorithms, robotics, and analytics, among other digital technologies, are revolutionizing the dynamics of the workforce in organizations. Hence, the writers of this study have examined the consequences of emerging technology on Organizational Behavior. A significant proportion of the existing research on this topic has primarily examined the technology aspects, while neglecting the comprehensive perspective and its impact on organizational behavior. The uniqueness of this study resides in its ability to offer a comprehensive overview of the key digital technologies and assess their impact on employees and leadership. In order to achieve this objective, and considering the current relevance of the subject, the authors chose to examine the effects of digital technologies on organizational behavior. They accomplished this by conducting a thorough analysis of existing literature and organizing it according to the specific technologies and their implications. The article is divided into three sections. Firstly, the definitions of Organizational Behavior and digitalization were examined to establish a theoretical framework. This was followed by an analysis of the impacts and effects of digitalization on leadership and employees. Finally, the findings were summarized in a structured scheme.

Navigating the AI Revolution in Business Management: New Strategies and Innovations

By Mustakim Bin Aziz

Artificial Intelligence (AI) has changed a paradigm shift in business management, presenting unprecedented opportunities for innovation and strategic enhancement. This research explores the transformative impact of AI technologies on contemporary business practices. This paper presents, how AI reshapes decision-making processes, optimizes operational efficiency, and fuels innovative strategies to maintain competitive advantage in a rapidly evolving market. Through case studies and a comprehensive analysis of industry applications, the research identifies key AI-driven tools and methods that revolutionize various aspects of business management, including supply chain optimization, customer relationship management, and predictive analytics. The study also examines the challenges and ethical considerations associated with AI integration, providing insights into best practices for successful implementation. By synthesizing theoretical frameworks with practical examples, this study aims to provide a holistic understanding of the dynamic interplay between AI and business management. It emphasizes the need for businesses to adapt to this technological revolution and outlines strategic recommendations for using AI to drive sustainable growth and innovation. By synthesizing theoretical frameworks with practical examples, this thesis aims to offer a holistic understanding of the dynamic interplay between AI and business management. It underscores the necessity for businesses to adapt to this technological revolution and outlines strategic recommendations for leveraging AI to drive sustainable growth and innovation.

Dynamic Analysis of a G+13 Story RCC Building Using Shear Wall in Three Different Locations on Various Seismic Zones

By Md. Kawsarul Islam Kabbo

Currently, Seismic impacts are a very serious concern when designing multi-storied reinforced concrete structures. Seismic tremors have occurred in numerous parts of the globe. High-rise structures should have proper stiffness to resist lateral loads caused by Earthquakes and Winds. Consequently, Engineers are extremely concerned about finding suitable solutions that will allow structures to survive without major damage. Shear walls are structural members that are designed to carry earthquake loads and oppose lateral loads significantly. They are a good choice to increase the stiffness of high-rise structures. This paper aims to use shear walls in various locations of a G+13 multi-storied residential building and to determine the best shear wall placement in high slender buildings by analyzing story displacement, story drift, base shear, and the fundamental time period in various seismic zones according to IS 1893:2016. Three models are prepared and compared under different seismic zones. Shear walls are at the core of the building, and shear walls are at the four corners of the building, which is a combination of both. Our study's goal is to test a structure's ability to bear lateral load applied to it according to the Code and also when it exceeds the limit of allowable deformation. The prepared model for this experimentation is considered to be located on medium soil, and wind velocity is high, like 148mph. The experiment concluded that building with a shear wall combination of both core and corner will show better results in resisting lateral forces, though the combination isn’t enough to help withstand the high slender structure against very powerful earthquake attacks like Zone-V.

Intelligence-driven Risk Management in Information Security Systems

By Anamika Tiwari

The task of making decisions in information security, when faced with unclear probabilities and unforeseen consequences of events in the constantly evolving cyber threat landscape, has gained significant importance. Cyber threat intelligence equips decision-makers with essential information and context to comprehend and predict future threats, hence minimizing ambiguity and enhancing the precision of risk assessments. Addressing uncertainty in decision-making demands the adoption of a new methodology led by threat intelligence (TI) and a risk analysis approach. This is a crucial aspect of evidence-based decision-making. Our proposed solution to this difficulty involves the implementation of a TI-based security assessment methodology and a decision-making strategy that takes into account both known unknowns and unknown unknowns. The proposed methodology seeks to improve decision-making quality by utilizing causal graphs, which provide an alternative to current methodologies that rely on attack trees, hence reducing uncertainty. In addition, we analyze strategies, methods, and protocols that are feasible, likely, and credible, enhancing our capacity to anticipate enemy actions. Our proposed approach offers practical counsel to information security leaders, enabling them to make well-informed decisions in uncertain circumstances. This paper presents a novel approach to tackling the problem of making decisions in uncertain situations in the field of information security. It introduces a methodology that can assist decision-makers in navigating the complexities of the ever-changing and dynamic world of cyber threats.

Forecasting Financial Crashes with Advanced Time-Series Methods: A Predictive Framework

The research involves examining how financial markets, particularly the NASDAQ and S&P 500 indices, react when under stress, as well as applying advanced time series techniques in an attempt to predict crashes. Accurate prediction of crashes is important due to the tremendous impact financial market collapses, including the 2008 and COVID-19 epidemics, have on the worldwide economy. To model non-linear market dynamics, the study combines dynamic GARCH extensions and wavelet-based time series decomposition with ARIMA and GARCH models to forecast market volatility. The sample period ranged from January 2021 to August 2024, with total observations of 787 and 921 for the S&P500 and NASDAQ, respectively. The selection of the ARIMA and GARCH models was confirmed by the ADF and PP tests to determine whether the time series is stationary. The GARCH model with the GARCH effect of 0.912741 has most certainly accommodated the volatility clustering phenomenon, due to which an episode of high (low) volatility was followed by another episode of the same kind and successive spikes in the volatility, especially in the case of NASDAQ. The volatility persistence of the S&P 500 was lower (0.6785330 GARCH effect). For a relatively small level autoregressive table, the forecasts demonstrate that the variance of S&P 500 substantially increases in high volatility periods for most by up to 0.006. The NASDAQ was somewhat more persistent, as indicated by a variance of 0.00024. These findings illustrate how efficiently the proposed forecasting model is able to predict market crashes and offer valuable information for investors and policymakers.