This document is a working paper published for early dissemination and public access via Zenodo. It has not undergone formal peer review. The content reflects the author's original technical work, insights, and applied use of machine learning in real-world domains. This version is archived for academic and professional visibility and may be updated in the future based on community feedback or further development. The content was originally published as a technical article on https://prakashkota.com on April 9, 2005, and has been reformatted into this working paper for citation and archival purposes. Abstract This article presents a hands-on case study demonstrating the application of a lightweight neural network to forecast NVIDIA's (NVDA) next-day stock closing prices. Utilizing five years of historical data (2020–2024) and focusing on five key features—Open, High, Low, Close, and Volume—the model aims to predict the subsequent day's closing price. The study highlights the model's performance, noting a high correlation (R² = 0.9978) on training data and a reasonable correlation (R² = 0.8173) on unseen data. While acknowledging the model's limitations in accounting for unforeseen market events, the article underscores the potential of simple neural network architectures in providing valuable insights into stock price movements.