arXiv research

Study uses CNN and LSTM to recognize stock chart patterns.

Deep learning predicts stock market trends using candlestick charts.

Deep Q-Network predicts global stock market returns from chart images.

Deep CNN model uses stock bar charts for trading, outperforming Buy and Hold.

Model predicts Bitcoin's future movements using multimodal pattern matching.

Enhances trading signals using image analysis and weighted moving averages.

A surprising image of the stock market arises if the price time series of all Dow Jones Industrial Average stock components are represented in one chart at once. The chart evolves into a braid representation of the stock market by taking into account only the crossing of stocks and fixing a convention defining overcros…

Deep CNN model predicts stock prices with high accuracy.

The paper monitors stock market relationships using network analysis and statistical control charts.

Charts are an excellent way to convey patterns and trends in data, but they do not facilitate further modeling of the data or close inspection of individual data points. We present a fully automated system for extracting the numerical values of data points from images of scatter plots. We use deep learning techniques t…

Proposes a method to improve stock index prediction using cointegration and quantile loss.

We propose a new indicator for technical analysis. The indicator emphasizes maximums and minimums in price series with inherent smoothing and has a potential to be useful in both mechanical trading rules and chart pattern analysis.

Stock markets show unusual overnight and intraday returns.

Meta-learning predicts stock trading volumes by learning from each stock's unique patterns.

FinVision uses LLM agents to predict stock markets by processing various financial data types.

We propose a novel investment decision strategy (IDS) based on deep learning. The performance of many IDSs is affected by stock similarity. Most existing stock similarity measurements have the problems: (a) The linear nature of many measurements cannot capture nonlinear stock dynamics; (b) The estimation of many simila…

Paper proposes TRA to learn multiple stock trading patterns.

Proposes a new stock prediction method that accounts for market dynamics.

Study compares price patterns of cryptocurrencies and stocks using machine learning.

No minimal charts with exactly seven white vertices found.

Silence on suspicious stock market patterns persists despite lack of plausible explanations.

Moon phases added to stock market analysis for better pattern recognition.

This paper studies minimal charts of a specific type to understand embedded surfaces in 4-space.

In this paper, we give definitions of three kinds of minimal charts, and we investigate properties of minimal charts and establish fundamental theorems characterizing minimal charts. To classify charts with two or three crossings we use the fundamental theorems. In the future paper, we give an numeration of the charts …

We use high-frequency data of 1364 Chinese A-share stocks traded on the Shanghai Stock Exchange and Shenzhen Stock Exchange to investigate the intraday patterns in the bid-ask spreads. The daily periodicity in the spread time series is confirmed by Lomb analysis and the intraday bid-ask spreads are found to exhibit $L$…

No minimal chart of type (7) exists.

No minimal chart of type (4,3) exists in 4-space.

Paper classifies surface-links using charts with specific properties.

Market Mill is a complex dependence pattern leading to nonlinear correlations and predictability in intraday dynamics of stock prices. The present paper puts together previous efforts to build a dynamical model reflecting the market mill asymmetries. We show that certain properties of the conditional dynamics at a sing…

The paper studies 4-charts with three crossings and their equivalence to a specific knot.

No minimal chart of type (2,3,2) exists.

No minimal chart of type (3,2,2) exists.

Minimal charts of specific type contain unique subgraphs.

In this paper, we shall show a condition for that a chart is C-move equivalent to the product of two charts, the union of two charts $Γ^*$ and $Γ^{**}$ which are contained in disks $D^*$ and $D^{**}$ with $D^*\cap D^{**}=\emptyset$.

An empirical study of joint bivariate probability distribution of two consecutive price increments for a set of stocks at time scales ranging from one minute to thirty minutes reveals asymmetric structures with respect to the axes y=0, y=x, x=0 and y=-x. All four asymmetry patterns remarkably resemble a four-blade mill…

Support Vector Data Description (SVDD) is a machine learning technique used for single class classification and outlier detection. SVDD based K-chart was first introduced by Sun and Tsung for monitoring multivariate processes when underlying distribution of process parameters or quality characteristics depart from Norm…

Large and stable indices of the world wide stock markets such as NYSE and SP 500 together with NASDAQ -- the index representing markets of new trends, and WIG -- the index of the local stock market of Eastern Europe, are considered. Due to the relation between artificial insymmetrised patterns (AIP) and time series, st…

Motivated by the literature on investment flows and optimal trading, we examine intraday predictability in the cross-section of stock returns. We find a striking pattern of return continuation at half-hour intervals that are exact multiples of a trading day, and this effect lasts for at least 40 trading days. Volume, o…

A method to fix radius distortion in generative models on curved spaces.

Agent Trading Arena trains LLMs in real-time financial markets to improve numerical reasoning.

Paper improves channel charting using autoencoders with spatial constraints.

We studied non-dynamical stochastic resonance for the number of trades in the stock market. The trade arrival rate presents a deterministic pattern that can be modeled by a cosine function perturbed by noise. Due to the nonlinear relationship between the rate and the observed number of trades, the noise can either enha…

A branched covering surface-knot is a surface-knot in the form of a branched covering over an oriented surface-knot $F$, where we include the case when the covering has no branch points. A branched covering surface-knot is presented by a graph called a chart on a surface diagram of $F$. We can simplify a branched cover…

Let $Γ$ be a chart. For each label $m$, we denote by $Γ_m$ the "subgraph" of $Γ$ consisting of all the edges of label $m$ and their vertices. Let $Γ$ be a minimal chart of type $(m;3,3)$. That is, a minimal chart $Γ$ has six white vertices, and both of $Γ_m\capΓ_{m+1}$ and $Γ_{m+1}\capΓ_{m+2}$ consist of three white ve…

A 2-dimensional braid over an oriented surface-knot $F$ is presented by a graph called a chart on a surface diagram of $F$. We consider 2-dimensional braids obtained by an addition of 1-handles equipped with chart loops. We introduce moves of 1-handles with chart loops, called 1-handle moves, and we investigate how muc…

Agent-based model for two stocks using superhedging.

The existence of forbidden patterns, i.e., certain missing sequences in a given time series, is a recently proposed instrument of potential application in the study of time series. Forbidden patterns are related to the permutation entropy, which has the basic properties of classic chaos indicators, thus allowing to sep…

A branched covering surface-knot over an oriented surface-knot $F$ is a surface-knot in the form of a branched covering over $F$. A branched covering surface-knot over $F$ is presented by a graph called a chart on a surface diagram of $F$. For a branched covering surface-knot, an addition of 1-handles equipped with cha…