An Efficient Deep Learning Based Model to Predict Interest Rate Using Twitter Sentiment

Abstract

In macroeconomics, decision making is highly sensitive and significantly influences the financial and business world, where the interest rate is a crucial factor. In addition, the interest rate is used by the governments to manage the monetary policy. There is a need to design an efficient algorithm for interest rate prediction. The analysis of the social media sentiment impact on financial decision making is also an open research area. In this study, we deploy a deep learning model for the accurate forecasting of the interest rate for the UK, Turkey, China, Hong Kong, and Mexico. For this purpose, daily data of the interest rate and exchange rate covering the period from Jan 2010 to Oct 2019 is used for all the mentioned countries. We also incorporate the input of the twitter sentiments of six mega-events, namely the US election 2012, Mexican election 2012, Gaza under attack 2014, Hong Kong protest 2014, Refugee Welcome 2015, and Brexit 2016. Our results provide evidence that the error of the deep learning model significantly decreases when event sentiment is incorporated. A notable improvement has been observed in the case of the Hong Kong interest rate, i.e., a 266% decline in the error after incorporating event sentiments as an input in the deep learning model.

A Review of Deep Learning Models for Twitter Sentiment Analysis: Challenges and Opportunities

“…To gain better insights into recent years' advancements, the current survey bifurcates the DL literature into a taxonomy broadly categorized as Basic and Transformer-based. Basic DL models consist of Deep Neural Network (DNN) [32,33,34], Convolutional Neural Network (CNN), [35,36,37,38], Recurrent Neural Network (RNN) [40], Long Short-Term Memory (LSTM) [110] whereas Transformer-based includes BERT [111], RoBERTa [112], XLNet [113], and GPT [114] etc. Besides, these two major categories there are many DL-hybrid methods proposed by the research community for Twitter text sentiment analysis along with recent developments of Graphbased methods that are classified under the "other" category in the current study.…”

“…To address these limitations, deep learning, a cluster of multi-layer neural network algorithms have emerged as a promising sub-field of machine learning for Twitter sentiment analysis [32,33,34]. Several deep learning-based models, including Deep (Vanilla) Neural Networks (DNN) Ali et al [32], Yasir et al [34], Convolutional Neural Networks (CNN) [35,36,37,38], Recurrent Neural Networks (RNN) [39,40], and their variants such as Long Short-Term Memory (LSTM) [41,42,43,44], Gated Recurrent Units (GRU) and hybrid techniques have shown effectiveness in capturing the nuances of natural language and handling the noise and ambiguity present in Twitter data [35,36,37,38,39,40,41,42,43,44]. These models offer flexible solutions that enhance sentiment analysis performance by providing a better interpretation of the context and semantic meaning of text data.…”

A Proposal of Transfer Learning for Monthly Macroeconomic Time Series Forecast

“…Some studies have used deep learning to generate forecast models for macroeconomic variables such as exchange rate [5], inflation [2], unemployment rate [15], GDP [16], interest rate [17], and exports [11]. The periodicity of the time series used is diverse, and ranges from daily to annual.…”

“…Some models only use the lagged values of the time series as an input to the neural network e.g., [10,18], while others also use the lagged values of other time series e.g., [2,4]. A particular case is the model of [17], who incorporated Twitter sentiment related to multiple events happening around the globe into interest rate prediction.…”

Privacy Prevention of Big Data Applications: A Systematic Literature Review

“…In order to meet the restrictions of traditional detection approaches, machine learning methods may be used (Firdausi et al, 2010). ML applications in many life sectors, including as education, health, business, and cybersecurity (Yasir et al, 2020) are being expanded (Jusas & Samuvel, 2019; Manjula & Anandaraju, 2018; Shaukat Dar & Ulya Azmeen, 2015).…”