Browsing by Author "Aryal, S"

Filter results by typing the first few letters
Now showing 1 - 6 of 6
  • Thumbnail Image
    PublicationOpen Access
    Comparative Analysis of Deep Learning Models for Multi-Step Prediction of Financial Time Series
    (researchgate.net, 2020-10-21) Aryal, S; Nadarajah, D; Rupasinghe, P.L; Jayawardena, C; Kasthurirathna, D
    Financial time series prediction has been a key topic of interest among researchers considering the complexity of the domain and also due to its significant impact on a wide range of applications. In contrast to one-step ahead prediction, multi-step forecasting is more desirable in the industry but the task is more challenging. In recent days, advancement in deep learning has shown impressive accomplishments across various tasks including sequence learning and time series forecasting. Although most previous studies are focused on applications of deep learning models for single-step ahead prediction, multi-step financial time series forecasting has not been explored exhaustively. This paper aims at extensively evaluating the performance of various state-of-the-art deep learning models for multiple multi-steps ahead prediction horizons on real-world stock and forex markets dataset. Specifically, we focus on Long-Short Term Memory (LSTM) network and its variations, Encoder-Decoder based sequence to sequence models, Temporal Convolution Network (TCN), hybrid Exponential SmoothingRecurrent Neural Networks (ES-RNN) and Neural Basis Expansion Analysis for interpretable Time Series forecasting (N-BEATS). Experimental results show that the latest deep learning models such as NBEATS, ES-LSTM and TCN produced better results for all stock market related datasets by obtaining around 50% less Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) scores for each prediction horizon as compared to other models. However, the conventional LSTM-based models still prove to be dominant in the forex domain by comparatively achieving around 2% less error values.
  • Thumbnail Image
    PublicationEmbargo
    Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction
    (2019-12-05) Nadarajah, D; Aryal, S; Kasthurirathna, D; Rupasinghe, L; Jayawardena, C
    Forecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.
  • Thumbnail Image
    PublicationEmbargo
    Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction
    (IEEE, 2019-12-05) Aryal, S; Nadarajah, D; Kasthurirathna, D; Rupasinghe, L; Jayawardena, C
    Forecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.
  • Thumbnail Image
    PublicationEmbargo
    Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction
    (IEEE, 2019-12-05) Aryal, S; Nadarajah, D; Kasthurirathna, D; Rupasinghe, L; Jayawardena, C
    Forecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.
  • Thumbnail Image
    PublicationEmbargo
    MoocRec: Learning styles-oriented MOOC recommender and search engine
    (IEEE, 2019-04-08) Aryal, S; Porawagama, A. S; Hasith, M. G. S; Thoradeniya, S. C; Kodagoda, N; Suriyawansa, K
    Massive Open Online Courses (MOOCs) are the new revolution in the field of e-learning, providing a large number of courses in different domains to a wide range of learners. Due to the availability of several MOOC providers (including edX, Coursera, Udacity, FutureLearn), a specific domain has multiple courses spread across these platforms that confuses a learner on selecting the most suitable course for him. It is a tedious manual task for the learner to browse through various courses before he finds the best course that meets his learning requirements and objectives. MoocRec is a unique learning styles-oriented system that recommends the most suitable courses to a learner from different MOOC platforms based on their learning styles and individual needs. The courses are recommended based on the mapping of Felder and Silverman learning styles with the standard video styles used in MOOC videos (including talking head, slide, tutorial/demonstration). MoocRec also allows the learners to search for courses using specific topics to provide an enhanced personalized learning environment. Results show that MoocRec is strongly reliable and can be used for personalized learning.
  • Thumbnail Image
    PublicationEmbargo
    Using Pre-trained Models As Feature Extractor To Classify Video Styles Used In MOOC Videos
    (IEEE, 2018-12-21) Aryal, S; Porawagama, A. S; Hasith, M. G. S; Thoradeniya, S. C; Kodagoda, N; Suriyawansa, K
    Massive Open Online Courses (MOOCs) have emerged as new learning phenomenon in the field of e-learning. Over recent years, it has attracted a significant number of learners as well as researchers. A wide range of researches is being carried out across multiple aspects of MOOCs. Video lectures are the most fundamental component in a MOOC. There are standard video styles that are normally used across several MOOC platforms, such as, talking head, demonstration, slides, animation etc. This paper presents an Image-Based classification approach of the video styles where a single video is split into multiple image frames, and then each frame is classified into one of the video style-category. Different classifier models built on top of each state-of-the-art deep neural architectures, including VGG16, InceptionV3, and ResNet50 are evaluated and the comparison of results is shown. Furthermore, the paper also discusses a numeric method to calculate the composition level of a single video style in multi-style filed videos based on the classification results.