Navin Chhibber

Improving Stock Price Forecasting Using Neural Prophet and MLP-Based Deep Neural Networks

Abstract:

Stock market price prediction is a complex interdisciplinary challenge involving finance, statistics, and economics. Traditional statistical time-series models often find it difficult to accurately represent the probability distribution of future stock prices. To overcome this challenge, this study introduces a Neural Prophet with Deep Neural Network (NP-DNN) approach for stock price forecasting. The model utilizes Z-score normalization to eliminate scale differences and imputes missing values to enhance data completeness. A Multi-Layer Perceptron (MLP) is employed to learn nonlinear relationships and extract meaningful features from historical price data. Experimental results show that the proposed NP-DNN model achieves 99.21% accuracy, surpassing existing methods, including those based on Fused Large Language Models (LLMs).

Profile:

Navin Chhibber is a Product Engineering leader and entrepreneur with 20+ years of experience driving innovation at the intersection of AI/ML, data, and digital transformation. Backed by advanced education in business, economics, and computer science, including an MBA from Boston University, a Master’s in Business Economics, and a Master’s in Computer Applications, Navin combines strategic leadership with deep technical expertise.
Throughout his career, he has launched 12+ B2B/B2C products and delivered 10 mission-critical AI and data platforms across eCommerce, FinTech, Retail, and Telecom. Navin’s work spans delivering real-time risk and fraud detection models at Visa that processed 200,000 transactions per second with 5 ms latency, preventing over $30B in potential fraud, to designing NVIDIA GPU-powered ML training platforms for data scientists. He has also led initiatives at Walmart, AT&T, Apple, and PayPal that delivered significant business outcomes, including over $50 million in annual operational savings and a 5% increase in eCommerce conversion rate through enhanced customer experience and intelligent automation. Additionally, he has contributed to 5 successful M&A and integration initiatives across data, platform engineering, and enterprise transformation.
In addition to his product and engineering leadership roles, he mentors startup and emerging-technology founders, helping them shape product strategy, go-to-market plans, and scalable Data & AI architectures, with a strong focus on enhancing the customer experience through personalization, seamless digital journeys, and measurable business outcomes. He also speaks and writes on emerging technologies and product innovation.