Zareen Alamgir

Forecasting stock market closing prices is a critical task for business intelligence, as it provides insights for financial planning and decision-making. The complexity arises due to diverse market patterns and various external factors that influence stock prices. This study presents a robust framework that incorporates market styles, economic indicators and news sentiments to enhance prediction power. The machine learning models are trained on aggregated datasets from companies exhibiting similar market styles. Experiments using Yahoo Finance data from five major companies (Apple, Amazon, Google, Meta, and Nike) show that accurate identification of market styles by the proposed model significantly improves pattern detection, while sentiment and economic indicators further enhance prediction quality. The findings demonstrate how multi-factor modeling can strengthen business intelligence systems by providing more reliable forecasts and supporting data-driven financial strategies.

Educational data mining is widely deployed to extract valuable information and patterns from academic data. This research explores new features that can help predict the future performance of undergraduate students and identify at-risk students early on. It answers some crucial and intuitive questions that are not addressed by previous studies. Most of the existing research is conducted on data from 2-3 years in an absolute grading scheme. We examined the effects of historical academic data of 15 years on predictive modeling. Additionally, we explore the performance of undergraduate students in a relative grading scheme and examine the effects of grades in core courses and initial semesters on future performances. As a pilot study, we analyzed the academic performance of Computer Science university students. Many exciting discoveries were made; the duration and size of the historical data play a significant role in predicting future performance, mainly due to changes in curriculum, faculty, society, and evolving trends. Furthermore, predicting grades in advanced courses based on initial pre-requisite courses is challenging in a relative grading scheme, as students’ performance depends not only on their efforts but also on their peers. In short, educational data mining can come to the rescue by uncovering valuable insights from academic data to predict future performance and identify the critical areas that need significant improvement.

Road traffic prediction is a crucial area currently investigated under the umbrella of the intelligent transportation system. Timely and accurate traffic prediction is a challenging problem because of the diverse nature of roads, abrupt changes in speed, and the existence of dependencies between road segments. A critical component of this research is addressing the dynamic spatial and non-linear temporal dependencies in the road network. The traffic conditions in a traffic road network change continuously, and for precise predictions, time-varying spatial correlation needs to be integrated into the model. This study intends to incorporate dynamic spatial dependencies in the Graph WaveNet model by applying attention mechanisms that can compute attention scores for the self-adaptive adjacency matrix in the time domain. We compared the computation cost of our proposed model of a graph attention network with multi-head attention with Graph WaveNet for up to 60 min. Our model gave the best result for 60-min prediction with an average percentage decrease of 3.4% and 4.76% in root-mean-square error on PEMS-BAY and METR-LA datasets, respectively. However, the model training time is increased because of the added computation of attention scores.