Paper: arXiv 2305.14378

Authors: Aadhitya A, Rajapriya R, Vineetha R S, Anurag M Bagde

Abstract

Stock market is often important as it represents the ownership claims on businesses. Without sufficient stocks, a company cannot perform well in finance. Predicting a stock market performance of a company is nearly hard because every time the prices of a company stock keeps changing and not constant. So, its complex to determine the stock data. But if the previous performance of a company in stock market is known, then we can track the data and provide predictions to stockholders in order to wisely take decisions on handling the stocks to a company. To handle this, many machine learning models have been invented but they didn’t succeed due to many reasons like absence of advanced libraries, inaccuracy of model when made to train with real time data and much more. So, to track the patterns and the features of data, a CNN-LSTM Neural Network can be made. Recently, CNN is now used in Natural Language Processing (NLP) based applications, so by identifying the features from stock data and converting them into tensors, we can obtain the features and then send it to LSTM neural network to find the patterns and thereby predicting the stock market for given period of time. The accuracy of the CNN-LSTM NN model is found to be high even when allowed to train on real-time stock market data. This paper describes about the features of the custom CNN-LSTM model, experiments we made with the model (like training with stock market datasets, performance comparison with other models) and the end product we obtained at final stage.

Complexity vs Empirical Score

  • Math Complexity: 3.0/10
  • Empirical Rigor: 4.5/10
  • Quadrant: Philosophers — conceptual discussion, lower math and empirical scores

Why this score: The paper primarily applies standard deep learning architectures (CNN-LSTM) with minimal advanced mathematics, relying on existing libraries and methods. However, it discusses real-time data, API usage, and deployment (Docker), but lacks detailed backtesting, rigorous statistical validation, or novel implementation specifics that would indicate strong empirical readiness.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Predict Stock Market Trends<br>using Deep Learning"] --> B["Data Input:<br>Historical Time-Series Stock Data"]
  B --> C["Methodology:<br>CNN-LSTM Neural Network Model"]
  C --> D["Process 1:<br>CNN extracts spatial features<br>from data tensors"]
  D --> E["Process 2:<br>LSTM analyzes temporal patterns<br>in sequence data"]
  E --> F["Training & Testing:<br>Real-time data evaluation"]
  F --> G{"Outcomes & Findings"}
  G --> H["Key Finding 1:<br>High Prediction Accuracy"]
  G --> I["Key Finding 2:<br>Superior to traditional<br>machine learning models"]
  G --> J["Key Finding 3:<br>Effective for<br>real-time forecasting"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes a custom CNN‑LSTM neural network model for predicting stock market time‑series data.

Source sentence
So, to track the patterns and the features of data, a CNN-LSTM Neural Network can be made.

Assumes 1

  • The model can be trained on real‑time stock market data and achieve high accuracy. data
    Source sentence
    The accuracy of the CNN-LSTM NN model is found to be high even when allowed to train on real-time stock market data.

Data

  • Kaggle mixed stock market sample data · Kaggle market-prices public
    Source sentence
    We tested and experimented the model with different datasets from Kaggle consisting sample data of mixed content from different stock markets
  • NASDAQ dataset market-prices unknown
    Source sentence
    NASDAQ dataset it occured while loading up the saved model.
  • Alpha Vantage API real‑time data · Alpha Vantage market-prices public
    Source sentence
    real time dataset by fetching data from Alpha Vantage API

Recognised sources: Kaggle Alpha Vantage

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • For the NIFTY dataset the model predicted up to 99% of stocks correctly during testing. predictive-accuracy
    Source sentence
    For NIFTY [11], the model proved to be good and predicted at most 99% of stocks even during the testing stage.
  • Training MSE ranged approximately from 0.001 to 0.05 and validation MSE from 0.002 to 0.1 across datasets. statistical
    Source sentence
    Also, we obtained MSE of value 0.001 to 0.05 (approx) during training and 0.002 to 0.1 (approx) for validation with different datasets.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 22 related papers). Coverage is partial, so this is neither replication nor refutation.

Cited by 3 papers in the archive (3 by independent authors)

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.