Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (2024)

Written by: Avinash Kumar Pandey (Research Associate, ISB Hyderabad)

Introduction:

In this article, we will learn how to apply deep convolutional networks for predicting 1D time-series/sequences in python. This model could be easily applied to the stock-price prediction problem. Deep CNNs have been quite popular in areas such as Image Processing, Computer Vision, etc. Recently, the research community has been showing a growing interest in using CNNs for time-series forecasting problems. This article will be useful for a wide range of readers including deep learning enthusiasts, finance professionals, academicians, and data-science hobbyists.

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (1)

Convolutional Neural Networks: Analogy between Computer Vision & Time Series Forecasting

In this section, we will start with an Image processing example to understand intuitively the similarity between Computer Vision and Time Series Analysis using CNNs. Let’s get started with the example involving this puppy (because it’s very cute).

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (2)

CNN’s interpretation of Image matrices

Every image that is digitally available is actually a matrix of pixel values. Each pixel value can range from 0 to 255 depending on the intensity of the pixel. Each image also comprises channels depending on the color composition of the image. A grey image has one channel since each channel corresponds to the colors it contains. A color image has three channels comprising red, blue, and green colors. A convolutional neural network perceives each image as a matrix of pixel values in the dimension of image width, length, and the number of channels.

For example, let us assume that the puppy’s image is 2000 pixels wide and 2500 pixels in height. Also, since it is a color image, it would have 3 channels. Hence, the image would consist of 3 matrices of the size of dimensions [2500,2000]. Overall, we have a 3D matrix of dimension [2500,2000,3]. This 3D matrix then goes in as an input to the CNN model. Therefore, for a CNN model the above image is interpreted (in an over-simplified example) as a matrix as shown below :

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (3)

Now that we have an understanding of how an image is perceived by the Machine Learning Model, we will proceed to understand the primary components of a Deep CNN model and understand how these components are also used for time series forecasting. Following are the primary layers of an ordinary CNN model.

1. Convolutional Layer

2. Pooling Layer

3. Fully Connected Layer

These layers are explained in brief for better understanding.

Convolutional Layer

In the convolutional layer, the image input matrix is multiplied by a feature matrix to extract important features of the image. The filter matrix slides through the input matrix and basically extracts the information from smaller sub-sections of the image. There are various filter matrices available to extract different types of features from the image. The figure below shows a basic filter operation on our input image matrix.

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (4)

Image Source: provided by the Author

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (5)

Pooling Layer

In the pooling layer, the resultant matrix is then multiplied to pooling matrix which extracts the maximum or average values from the small subsections. The pooled image is significantly compressed in size than the main image matrix. A basic illustration is shown below.

Fully Connected Layer

The pooled matrix is then flattened and then fed to the fully connected layer which learns the images through its neural networks. In our time series stock price forecasting example, the 1D time series is converted to a 3D matrix using the methodology below and the neural network analogy remains the same. A full flow chart for the application of CNN to time series prediction is shown below. The only difference between computer vision problems and time series ones is the input we give to the model (image matrix for computer vision and 1D array for time series forecast ).

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (7)

Hence, if we are able to convert the 1D time-series sequence to an input image matrix shape, we could apply a CNN model for the forecasting problem. We will now discuss the methodology and a simple test sequence on which we will apply our model.

Methodology for CNN model:

We will be following the below-mentioned pathway for applying CNNs to a univariate 1D time series :

1) Import Keras libraries and dependencies

2) Define a function that extracts features and outputs from the sequence.

3) Reshape the input X in a format that is acceptable to CNN models

4) Design the CNN model architecture of convolutional layers(Conv-1D), pooling(max-pooling in our case ), flattening layer, and the fully connected neural layers.

5) Train the model and test it on our univariate sequence.

Data

Important Note regarding the data sequence: In this article, I will be showing you how to apply a CNN model to a 1D time series sequence. For illustration purposes, we will be using a very simple sequence from [100 to 190 ] with a common difference of 10 and see if our CNN model is able to pick up on that. You can always use stock price time-series data from open sources such as yahoo finance by using python library yfinance and I would leave that exercise on the reader.

Code Section :

Step 1: Firstly, import all the libraries from Keras for neural network architectures.

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (8)

Step 2: Next, we will define a function that extracts features (lagged values) and outputs from the sequence.

As an example, let’s suppose the sub-sequence is [ 10, 20, 30, 40 ] and we decide to predict the sequence using the last two lagged values(defined as “steps” in the function). Then in our small example, the model will train and learn to predict the 3rd value (in our case “30”) using first and second values [10,20] as features. Similarly, the last value (“40”) will be predicted using two preceding terms ([20, 30]). Our function split_sequence creates such lists of features and outputs from the sequence and feeds the output to the model for training.

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (9)

Step 3: Initializing Sequence, steps, and reshaping the output to input it to our CNN model.

As explained in step 2, we have created a function that converts a 1D sequence into sub-sequences (features and predicted values). In this step, we will define an artificial sequence from 100 to 190 with a gap of 10. Obviously, we know that the next logical number in this sequence should be 200. Now, we would like to see if the CNN model is to learn the sequence pattern and predict the next terms.

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (10)

Output for the above section of code :

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (11)

After reshaping the X matrices we will get the output as shown below:

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (12)

Output for the above section of the code :

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (13)

Step 4: Defining CNN Model Architecture

In this step, we would define the model and put down the necessary setting for our model. We would be using “ReLu” as our activation function. We are adding Conv1D as our convolutional layer since we are dealing with a one-dimensional sequence. We then add the MaxPooling layer and Flatten layer for pooling and flattening of the input matrix to be served as an input to the fully connected neural networks (100 neurons) to learn the pattern in our sequence. Lastly, we set one neuron for our output (Dense = 1). We will be using mean squared error as our loss function with Adam (Adaptive Moment Estimator) as our optimizer in the gradient descent problem.

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (14)

Step 5: CNN Model Fitting

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (15)

Step 6: Running the Model:

Hands-On Stock Price Time Series Forecasting using Deep Convolutional Networks (16)

We see that the CNN model is able to identify the pattern and is able to predict the next steps. Full code is available at this Github link and you are free to use it. Also, code for multiple steps in the future is also included which you can use with stock price data.

Conclusion:

We learned how to convert a 1D univariate time series to an input matrix suitable for CNN model input. We then designed a Deep CNN model which was able to learn the pattern in the sequence and predict the output accurately. CNN models are popular for detecting the patterns in the pixel matrix via their convolutional layers. Similarly, upon suitable treatment, patterns (cyclical and trend components) in the time series data could be learned effectively by the CNN model.

Advanced CNN architecture, combined with other Deep Learning models such as LSTM could yield better performance. These models are currently being researched by academicians and practitioners alike.

About the Author :

Hi, My name is Avinash Pandey. I am passionate about Machine Learning applications in Finance and Portfolio Management. I am a graduate of IIT-BHU and currently working as a Research Associate in Finance Dept. at ISB Hyderabad. You can reach out to me on Linkedin or email me at [emailprotected].

References :

1) Artificial Intelligence in Finance (A python-based guide): Yves Hilpisch (O’Reilly Publication)

2)Chollet, François. 2017. Deep Learning with Python. Shelter Island: Manning

3)Cui, Chen, W., and Chen, Y. (2016). Multi-scale convolutional neural networks for
time series classification. arXiv preprint arXiv:1603.06995: https://arxiv.org/pdf/
1603.06995.pdf

4) Python for Finance Cookbook: Erik Lewinson (Packt Publishing)

FAQs

Can CNN be used for time series forecasting? ›

Key Advantages of CNNs for Time Series Forecasting:

Local Connectivity: CNNs employ convolutional layers that focus on local regions of the input data. This characteristic enables them to capture short-term patterns effectively, which is crucial in time series forecasting.

Discover More ›

Can CNN be used for stock prediction? ›

Because the stock data can be seen as a large 2D matrix, [3] has used ANN model to make prediction and gain a satisfied result, both of which have proved that CNN also can be used to do the same thing.

Learn More Now ›

Can we use deep learning for time series forecasting? ›

Deep learning, the currently leading field of machine learning, applied to time series forecasting can cope with complex and high-dimensional time series that cannot be usually handled by other machine learning techniques.

Discover More Details ›

Is LSTM better than CNN? ›

For the metric MAE, the LSTM model performs better than all other models in predicting lines 3, 4, and 5, while the model LSTM-CNN performs better than all other models in predicting lines 1 and 2 and the model CNN-LSTM performs better than all other models in predicting line 6.

See Details ›

Which machine learning algorithm is best for time series forecasting? ›

The Best Time Series forecasting algorithms are the following: Autoregressive. Exponential Smoothing (ES) Autoregressive Moving Average (ARMA)

What is the best algorithm for predicting stock prices? ›

The LSTM algorithm has the ability to store historical information and is widely used in stock price prediction (Heaton et al. 2016). For stock price prediction, LSTM network performance has been greatly appreciated when combined with NLP, which uses news text data as input to predict price trends.

Discover More ›

Is it possible to predict stock prices with a neural network? ›

Utilizing a Keras LSTM model to forecast stock trends

At the same time, these models don't need to reach high levels of accuracy because even 60% accuracy can deliver solid returns. One method for predicting stock prices is using a long short-term memory neural network (LSTM) for times series forecasting.

Which model is best for stock price prediction? ›

ARIMA is a very popular statistical method for time series forecasting. ARIMA models take into account the past values to predict the future values. There are three important parameters in ARIMA: p (past values used for forecasting the next value)

Get More Info Here ›

What is the best AI model for stock prediction? ›

We screened 69 titles and read 43 systematic reviews, including more than 379 studies, before retaining 10 for the final dataset. This work revealed that support vector machines (SVM), long short-term memory (LSTM), and artificial neural networks (ANN) are the most popular AI methods for stock market prediction.

Read On ›

Is ARIMA better than LSTM for stock market prediction? ›

The longer the data window period, the better ARIMA performs, and the worse LSTM performs. The comparison of the models was made by comparing the values of the MAPE error. When predicting 30 days, ARIMA is about 3.4 times better than LSTM. When predicting an averaged 3 months, ARIMA is about 1.8 times better than LSTM.

Keep Reading ›

What is the best neural network for time series? ›

Recurrent Neural Networks (RNNs) The Recurrent Neural Network (RNN) is one of the promising ANNs that has shown accurate results for time series forecasting. It is made up of a series of interconnected neural networks at different time intervals or time steps.

Keep Reading ›

What is the best model for time series forecasting? ›

ARIMA and SARIMA

AutoRegressive Integrated Moving Average (ARIMA) models are among the most widely used time series forecasting techniques: In an Autoregressive model, the forecasts correspond to a linear combination of past values of the variable.

Discover More ›

Can you use XGBoost for time series forecasting? ›

The common cases for the XGBoost applications are for classification prediction, such as fraud detection, or regression prediction, such as house pricing prediction. However, extending the XGBoost algorithm to forecast time-series data is also possible.

View Details ›

What is the difference between RNN and CNN for time series? ›

CNNs are commonly used to solve problems involving spatial data, such as images. RNNs are better suited to analyzing temporal and sequential data, such as text or videos.

See Details ›

Which neural network is best for time series classification? ›

Convolutional Neural Networks are the most popular Deep Learning technique for Time Series Classifications, since they are able to successfully capture the spatial and temporal patterns through the use of trainable filters, assigning importance to these patterns using trainable weights.

What model is used for time series forecasting? ›

AutoRegressive Integrated Moving Average (ARIMA) models are among the most widely used time series forecasting techniques: In an Autoregressive model, the forecasts correspond to a linear combination of past values of the variable.

Discover More ›

Can CNN be used for sequential data? ›

A CNN processes sequence data by applying sliding convolutional filters to the input. A CNN can learn features from both spatial and time dimensions. An LSTM network processes sequence data by looping over time steps and learning long-term dependencies between time steps.

View Details ›