No abstract

In practice, time series forecasting involves the creation of models that generalize data from past values and produce future predictions. Moreover, regarding financial time series forecasting, it can be assumed that the procedure involves phenomena partly shaped by the social environment. Thus, the present work is concerned with the study of the use of sentiment analysis methods in data extracted from social networks and their utilization in multivariate prediction architectures that involve financial data. Through an extensive experimental process, 22 different input setups using such extracted information were tested, over a total of 16 different datasets, under the schemes of 27 different algorithms. The comparisons were structured under two case studies. The first concerns possible improvements in the performance of the forecasts in light of the use of sentiment analysis systems in time series forecasting. The second, having as a framework all the possible versions of the above configuration, concerns the selection of the methods that perform best. The results, as presented by various illustrations, indicate, on the one hand, the conditional improvement of predictability after the use of specific sentiment setups in long-term forecasts and, on the other, a universal predominance of long short-term memory architectures.

In data science, time series forecasting is the process of utilizing past or present (known) observations of a target variable to make predictions about future (unknown) observations. Due to the usefulness of forecasting applications in numerous real-life problems, various Statistical and Machine Learning forecasting models have been proposed over recent years. The purpose of this chapter is to compare the performance of several contemporary forecasting models that are considered state of the art. These include Autoregressive Integrated Moving Average (ARIMA), Neural Basis Expansion Analysis (NBEATS), Probabilistic Time Series Modeling focusing on deep learning-based models and others. In the first section of this work a brief theoretical background of the methods is provided. Then, the experimental procedure is being described. For the comparison, 40 univariate time series of financial data that cover a 1-year period were used. A python repository of automated time series forecasting models (AtsPy) was exploited to run the experiments. For the final comparison three different metrics (RMSE, MAE and MAPE) were taken into consideration. The results of this extended experimental procedure are presented through various explanatory diagrams of the methods' performance in the final section.

No abstract

When forecasting financial time series, incorporating relevant sentiment analysis data into the feature space is a common assumption to increase the capacities of the model. In addition, deep learning architectures and state-of-the-art schemes are increasingly used due to their efficiency. This work compares state-of-the-art methods in financial time series forecasting incorporating sentiment analysis. Through an extensive experimental process, 67 different feature setups consisting of stock closing prices and sentiment scores were tested on a variety of different datasets and metrics. In total, 30 state-of-the-art algorithmic schemes were used over two case studies: one comparing methods and one comparing input feature setups. The aggregated results indicate, on the one hand, the prevalence of a proposed method and, on the other, a conditional improvement in model efficiency after the incorporation of sentiment setups in certain forecast time frames.