Quant Paper LogoQuant Paper
Quant WikiQuant WikiQuant QuestionJobs

Stock Market Price Prediction using Neural Prophet with Deep Neural Network

—

Stock Market Price Prediction using Neural Prophet with Deep Neural Network

Navin Chhibber
Sunil Khemka
Navneet Kumar Tyagi
Rohit Tewari
Bireswar Banerjee
Piyush Ranjan
Published on 1/8/2026
Stocks
Machine learning
Deep learning
Stock picking

This paper introduces a novel hybrid model, Neural Prophet with Deep Neural Network (NP-DNN), for stock market price prediction. The model combines the time-series forecasting capabilities of Neural Prophet with a Multi-Layer Perceptron (MLP) to capture both linear trends and complex nonlinear relationships in stock price data. Preprocessing steps include Z-score normalization to remove scale differences and missing value imputation to ensure complete data utilization. The proposed NP-DNN achieves an impressive accuracy of 99.21%, significantly outperforming existing methods such as Fused Large Language Models. The study highlights the effectiveness of integrating deep learning with traditional time-series models for financial forecasting, offering a robust solution for investors and researchers. The methodology is validated on historical stock data, demonstrating superior predictive performance and generalization.

Highlights

  • 1Proposes Neural Prophet with Deep Neural Network (NP-DNN) for stock price prediction, achieving 99.21% accuracy.
  • 2Integrates Neural Prophet with a Multi-Layer Perceptron to capture complex nonlinear relationships in stock data.
  • 3Uses Z-score normalization and missing value imputation for robust preprocessing.
  • 4Outperforms existing methods including Fused Large Language Model approaches.

Methods

  • M
    Neural Prophet with Deep Neural Network (NP-DNN) combining time-series forecasting with MLP.
  • M
    Z-score normalization for scaling stock price data.
  • M
    Missing value imputation to handle incomplete historical data.
  • M
    Multi-Layer Perceptron (MLP) for learning nonlinear patterns and feature extraction.

Results

  • R
    NP-DNN achieves 99.21% prediction accuracy on stock market data.
  • R
    Outperforms Fused Large Language Model and other baseline methods.
  • R
    Effective preprocessing (Z-score normalization and imputation) enhances model performance.
  • R
    Demonstrates robust generalization across different stock datasets.
0/5

Analyze Paper

Generate insights from "Stock Market Price Prediction using Neural Prophet with Deep...".

Suggested Actions