Explaining the causes of changes in complex financial markets can be helpful for future investment decisions. In this study, we focus on an anomaly in the financial market when the price movements of the Japanese stock index (TOPIX-17) and the Japanese government bond (JGB) interest rate are aligned. We analyze the changes in the financial markets from 2019 to 2020 in a descriptive manner by creating a graph with the data of the two regions of stocks and interest rates as nodes and using Graph-based Entropy (GBE) and Inter-regional Interaction. GBE is an index for detecting changes in the graph's structure, and Inter-regional Interaction is the variation in the regions where the data exist. The novelty of this study is to propose the indicator calculated from GBE and the Inter-regional Interaction to detect changes in financial markets considering the characteristics that before the price movements of stocks and interest rates are largely aligned, and the overall entropy goes down, but there is no interaction between regions. The result suggests that our proposed indicator can detect changes in the early stages that have not yet gone beyond regions but have been beginning to occur within regions, which lead to significant changes.
Financial market movements are complex. To detect market changes, explaining the state of the market at the time of those changes can be a great help in making investment decisions. The problem of change detection using only timeseries data is difficult to explain the causes and structure of change, and this is approached by using graphs and regions in this study.
: The i-th region in layer : the set of cross-regional clusters in across lower regions
The purpose of this study is to detect changes in the financial markets when the price movements of Japanese stock indices (TOPIX-17) and Japanese government bond (JGB) interest rate are aligned. Under normal conditions, the price movements are not so aligned between TOPIX-17, where the price movements are industry specific, and JGB interest rate, where the price movements are country specific. When an anomaly occurs, the price movements of stocks and bonds start to match each other. In a completely abnormal state, these price movements will be aligned in the same direction. In the late stage of the anomaly, the price movements will return to normal state. This study detects the point when the anomaly starts, no cross-regional impact yet (Low Inter-regional Interactions), but price movements within the region will be aligned (GBE starts to decrease).
We created a graph for each day, which includes 23 nodes
as TOPIX-17 and six JGB interest rates. For each time series
data, we (1) divided the time series by a window width of
10 days, (2) standardized the time series within the window,
and (3) calculated the distance between time series within
the window width for all combinations of nodes by DTW
To calculate Inter-regional Interactions., regions were set up using historical data. The two regions were divided by kmeans using the date and time data of the past five years (2014-2018) for 23 nodes. One region consists of the 17 TOPIX indexes excluding real estate (hereinafter called stock region) and the second is the six JGB interest rates and TOPIX real estate (hereinafter called bond region).
We applied our own index below.
Eq. (3) is an indicator that captures the moment when the
state transitions from normal to early abnormal, so that the
GBE drops while Inter-regional Interactions remains low.
We compared it with change point
In Figure 1, A, along with the change finder, reacted to a point in time prior to March 2020 when COVID-19 impacted the market. This is a good indication of the major changes that occurred in the market.
In Figure 2, where the threshold was loosened, only A reacted in July 2019. By loosening the threshold, we were able to capture smaller changes, and we believe that we detected the point in time when the market changed to the initial state of abnormality that would not show up in other methods.
In this study, we treated the stock price index and the interest rate on government bonds as two domains, and by looking at the interaction between the domains, we were able to detect the state of change in the financial market.
As future work, we would like to add further explanation of the content of structural change from the graph.