Analysis of the Term Structure of Major Currencies Using Principal Component Analysis and Autoencoders

Abstract

Recently, machine-learning algorithms and existing financial data-analysis methods have been actively studied. Although the term structure of government bonds has been well-researched, the majority of studies only analyze the characteristics of one country in detail using one method. In this paper, we analyze the term structure and determine the common factors using principal component analysis (PCA) and an autoencoder (AE). We collected data on the government bonds of three countries with major currencies (the US, the UK, and Japan), extracted features, and compared them. In the PCA-based analysis, we reduced the number of dimensions by converting the normalized data into a covariance matrix and checked the first five principal components visually using graphs. In the AE-based analysis, the model consisted of two encoder layers, one middle layer, and two decoder layers, and the number of nodes in the middle layer was adjusted from one to five. As a result, no significant similarity was found for each country in the dataset, and it was appropriate to extract three features in both methods. Each feature extracted by PCA and the AE had a completely different form, and this appears to be due to the differences in the feature extraction methods. In the case of PCA, the volatility of the datasets affected the features, but in the case of AE, the results seemed to be more affected by the size of the dataset. Based on the findings of this study, this topic can be expanded to compare the results of other machine-learning algorithms or countries.

Autoencoder-Based Feature Learning for Predicting Cardiovascular Disease

“…The Model Classifier can be trained and tested using the output. An autoencoder was used to extract the dimensions, after which they were converted into features for 27,26,25,24,23,22,21,20,19,18,14,10, and 6 neurons. The Autoencoder (AE) model is configured with the activation function at the bottleneck, encoder 1, encoder 2, decoder 1, and encoder 2 using Relu, the kernel initializer used is Random Normal with a standard deviation of 0.01, the initializer bias used is Zeros, and linear activation is used on the output layers.…”

“…Inputs in autoencoder can be reconstructed effectively with minimum reconstruction error [25]. Some researchers use autoencoder as a learning feature because it performs both linear and non-linear projections and outperforms PCA in the processing of complex, highdimensional datasets [26], [27]. Akkalakshmi [28], using Autoencoder in predicting cancer disease to determine latent features.…”

Forecasting the S&P 500 Index Using Mathematical-Based Sentiment Analysis and Deep Learning Models: A FinBERT Transformer Model and LSTM

“…Furthermore, the prediction of financial assets remains a critical topic within financial mathematics. Recent studies have demonstrated the remarkable performance of Artificial Neural Network (ANN)-based machine learning methodologies in predicting future data (Casado-Vara et al [14], Chae and Choi [15], Lin et al [16]). Our study takes an effective approach by utilizing the LSTM methodology to forecast the price of the S&P 500, contributing substantially to the growing body of knowledge in this area.…”

Uncovering the Impact of Local and Global Interests in Artists on Stock Prices of K-Pop Entertainment Companies: A SHAP-XGBoost Analysis

“…In contrast to traditional mathematical and statistical methods, machine learning models have been shown in multiple research studies to have better predictive accuracy (Kim et al [20], Shin et al [21], Grendas et al [22], Chae and Choi [23]). As a result, we have chosen to use the SHAP-XGBoost algorithm to predict stock prices for K-Pop entertainment companies.…”