DeepAI AI Chat
Log In Sign Up

Tangled String for Multi-Scale Explanation of Contextual Shifts in Stock Market

by   Yukio Ohsawa, et al.

The original research question here is given by marketers in general, i.e., how to explain the changes in the desired timescale of the market. Tangled String, a sequence visualization tool based on the metaphor where contexts in a sequence are compared to tangled pills in a string, is here extended and diverted to detecting stocks that trigger changes in the market and to explaining the scenario of contextual shifts in the market. Here, the sequential data on the stocks of top 10 weekly increase rates in the First Section of the Tokyo Stock Exchange for 12 years are visualized by Tangled String. The changing in the prices of stocks is a mixture of various timescales and can be explained in the time-scale set as desired by using TS. Also, it is found that the change points found by TS coincided by high precision with the real changes in each stock price. As TS has been created from the data-driven innovation platform called Innovators Marketplace on Data Jackets and is extended to satisfy data users, this paper is as evidence of the contribution of the market of data to data-driven innovations.


page 6

page 9

page 10

page 11


Design and Analysis of Robust Deep Learning Models for Stock Price Prediction

Building predictive models for robust and accurate prediction of stock p...

Nostradamus: Weathering Worth

Nostradamus, inspired by the French astrologer and reputed seer, is a de...

Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey

Predicting stock prices presents a challenging research problem due to t...

A statistical test of market efficiency based on information theory

We determine the amount of information contained in a time series of pri...

Modelling Information Incorporation in Markets, with Application to Detecting and Explaining Events

We develop a model of how information flows into a market, and derive al...

Switching Portfolios

A constant rebalanced portfolio is an asset allocation algorithm which k...

DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting

Stock trend forecasting is a fundamental task of quantitative investment...