Research
Unveiling Customer Sentiments: A Comprehensive Analysis of Product Reviews on Amazon
This research delves into the multifaceted implications of customer feedback within the e-commerce landscape, focusing on product reviews on Amazon. The study meticulously examines over 1,400 unique product reviews to decipher patterns, extrapolate trends, and offer actionable recommendations for the evolv- ing e-commerce paradigm. The dataset comprises 16 distinct features, including product ratings, textual re- views, prices, and discounts. Preliminary data explo- ration reveals a prevalence of high ratings, indicative of an overarching positive sentiment among Amazon’s clientele. Furthermore, features related to pricing and discounts hint at the intricate interplay between economic factors and customer feedback. Through data prepa- ration techniques, including numeric extraction and missing data handling, the research ensures the dataset’s readiness for advanced statistical and machine learning analyses. Leveraging the CRISP-DM methodology, the study uncovers insights into customer satisfaction, the impact of pricing strategies, and the significance of in- depth reviews. These findings provide actionable insights for e-commerce platforms and vendors, underscoring the importance of understanding customer sentiments for informed decision-making and cultivating positive customer relationships
Optimizing Real-Time Intelligent Traffic Systems with LSTM Forecasting and A* Search: An Evaluation of Hypervisor Schedulers
This research explores an Intelligent Traffic System (ITS) designed for real-time optimal routing using traffic forecasting and an A* search algorithm. Leveraging a pre-trained Long Short-Term Memory (LSTM) neural network, I predict traffic flow based on historical data to inform heuristic functions, ensuring optimal route calculations. The heuristic is constructed to be permissible and consistent by incorporating predicted traffic flow and average speed measurements. The experimental setup involves a messaging virtual machine (VM) and a real-time VM within a Xen hypervisor environment, utilizing Apache Kafka and Apache Flink for data flow and processing. I empirically evaluate the latency performance of the ITS under three different Xen schedulers: RTDS, Credit, and Credit2. My findings indicate that the RTDS scheduler provides superior latency guarantees, making it suitable for applications requiring ultra-low latency, whereas the Credit and Credit2 schedulers offer better median performance. These insights highlight the impact of hypervisor scheduler choice on the efficiency and responsiveness of real-time ITS applications.
Use of Robust Artificial Neural Networks and ARIMA in Detecting Brief Anomalies in Gas Consumption
This paper introduces an innovative system for outlier detection that combines the strengths of an Auto-regressive Integrated Moving Average (ARIMA) model and an Artificial Neural Network (ANN). While ARIMA is traditionally used for linear predictions and ANNs for non-linear forecasting, this study demonstrates their synergistic capabilities in capturing complex, non-linear relationships between meteorological forecast variables and gas consumption patterns. The resulting system can identify anomalies, aiding building managers in reducing energy waste in HVAC systems. The process comprises two phases: first, it predicts short-term gas consumption patterns using historical data, and then it identifies outliers by detecting deviations from expected values. Remarkably, this outlier detection process doesn’t require predefined labeled examples, thanks to the system’s highly accurate gas consumption forecasts, characterized by a root mean square error (RMSE) ranging from 8 m3 to 2.5 m3.
MERN Stack-Based Multi-Seller E-commerce Site
In almost every way, web development has been getting better and better over the last ten years. During this time, a number of frameworks and libraries came out, which made it much easier and faster to make a web app. Over the last decade, the LAMP stack (Linux, Apache, MySQL, and PHP) and Java-based applications have dominated web development. It was challenging for a single developer to construct a web application by using these stacks because of how complex they were. As the field of web development matured, MERN-an acronym for "MongoDB," "Express," "React," and "Node JS"-emerged as the dominant stack in 2023. Due to the relative simplicity of the technologies comprising this stack, a single developer may effectively handle both the front-end and back-end of the application. MongoDB, which is a no-SQL database; Express, which is a framework of Node JS used in back-end development; React, which is a JavaScript library used in front-end development; and NodeJS, which is an environment for JavaScript; these are the components that make up the MERN stack. The main goal of this thesis is to learn about the MERN stack and build a fully working multi-vendor e-commerce web application that is a laptop reselling platform. This application has a user-friendly interface, sign-up, and login systems that are JWT (JSON Web Token) secured. JWT is used to protect every API that this app uses. So that users don't have any problems, it's now easier to buy and sell used laptops. The interface and functionality of this app are designed with the user's ease of use in mind. The beta version of this is already completed and hosted in the server.
