Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

113226339452 · Jun 202019922001200920172026
48 results for market features

Study predicts electricity prices using LSTM models with feature selection, considering market coupling.

problem Accurate day-ahead electricity price forecasting in coupled markets.
method Hybrid LSTM-based deep learning models with feature selection algorithms.
result Proposed models achieve considerably accurate results in Nordic market.

Feature extraction from financial data is one of the most important problems in market prediction domain for which many approaches have been suggested. Among other modern tools, convolutional neural networks (CNN) have recently been applied for automatic feature selection and market prediction. However, in experiments …

2018-10-21abs ↗pdf ↗

The authors seek financial datasets to benchmark feature engineering methods on US market data.

problem Improving predictive models for financial data science competitions.
method Feature engineering methods applied to multivariate time-series data from the US market.
result Predictive power of models tested against Numerai-Signals targets.

Study finds Bitcoin market efficient, no exploitable inefficiencies with neural networks.

problem Investigating market inefficiencies in Bitcoin using neural networks.
method Used a feedforward neural network with various asset-related input features.
result Adding more features does not improve prediction accuracy, and one feature set outperforms a buy-and-hold strategy.

The performance of financial market prediction systems depends heavily on the quality of features it is using. While researchers have used various techniques for enhancing the stock specific features, less attention has been paid to extracting features that represent general mechanism of financial markets. In this pape…

2019-11-28abs ↗pdf ↗

The paper classifies market states to predict trading strategies, outperforming traditional methods.

problem Directly predicting prices or returns is unreliable; classifying market states is a better approach.
method Classify market states using various labels and features, then combine probabilities from neural networks.
result Trading strategy ensembles outperform traditional methods in returns and risk-adjusted returns.

The paper explores features from orderbooks to improve intraday electricity price forecasting.

problem Improving probabilistic forecasting of intraday electricity prices.
method Extracted 384 features from orderbooks, selected powerful features, and benchmarked models across two countries and product types.
result Revealed an asymmetric generalization phenomenon in electricity price forecasting models.

Model forecasts market structure from financial networks using machine learning.

problem Predicting market correlation structure from financial networks.
method Dynamic Asset Graph (DAG), Dynamic Minimal Spanning Tree (DMST), Dynamic Threshold Networks (DTN).
result Model improves market structure forecasting by up to 40% over benchmarks.

Optimizes LightGBM for stock market forecasting with novel feature engineering and transformation methods.

problem Accurately forecasting stock market fluctuations to mitigate risks.
method Feature engineering and transformation methods for LightGBM optimization.
result Log Returns, Returns and EMA Difference Ratio are the most effective target variable transformations.

Study compares altcoins to Bitcoin, analyzing their features and market performance.

problem Comparing altcoins to Bitcoin to understand market performance and features.
method Used Google Trend data, price, volume, and market capitalization data from coinmarketcap.com.
result Features of Litecoin, Zcash, Bitcoin Cash, Ethereum, and Bitcoin Gold affect market performance and user preferences.

Modeling price formation in intraday electricity markets with renewable generation.

problem Price formation and optimal trading strategies in intraday electricity markets with intermittent renewable generation.
method Developed a tractable equilibrium model using stochastic control theory to identify optimal strategies and exhibit Nash equilibrium.
result Identified optimal trading strategies and exhibited Nash equilibrium in closed form for a finite number of agents and in the asymptotic framework of mean field games.

Study proposes a new financial market representation for machine learning.

problem Complex analysis of financial time series for machine learning.
method Volume-price-based statistical approach.
result Proposed method outperforms price levels-based method on liquid markets.

Improved stock trading model using feature selection and ensemble learning.

problem Challenges in making profit in the US stock market.
method Feature selection from 148 to 30, dynamic selection of top 25 features, ensemble learning with four classifiers.
result Best model generated 54.35% profit over 18 months.

Model predicts risk-adjusted returns across various financial markets.

problem Stationary models fail in predicting risk-adjusted returns due to market regime changes.
method Asset-independent regime-switching model using hidden Markov models.
result Accurately detects bull, bear, and high volatility periods for improved risk-adjusted returns.

Financial markets are a typical example of complex systems where interactions between constituents lead to many remarkable features. Here, we show that a pairwise maximum entropy model (or auto-logistic model) is able to describe switches between ordered (strongly correlated) and disordered market states. In this frame…

2012-10-31abs ↗pdf ↗

This paper uses CNN-LSTM to predict stock market performance.

problem Predicting stock market performance is challenging due to changing prices and lack of advanced libraries.
method Developed a CNN-LSTM Neural Network model to track stock data patterns and predict future performance.
result The CNN-LSTM model outperformed other models in predicting stock market performance.

We propose the application of a high-speed maximum likelihood clustering algorithm to detect temporal financial market states, using correlation matrices estimated from intraday market microstructure features. We first determine the ex-ante intraday temporal cluster configurations to identify market states, and then st…

2015-08-20abs ↗pdf ↗

Study shows adding correlated features doesn't improve LSTM model interpretability for oil stocks.

problem Improving interpretability of LSTM models for predicting oil company stocks.
method Designed and trained Standard LSTM networks using various correlated datasets.
result Adding correlated features does not enhance LSTM model interpretability.

AlphaMLDigger predicts excess returns in fluctuating markets.

problem Mining effective information for investment decisions in a volatile market.
method Two-phase approach using deep NLP for sentiment analysis and ensemble ML models.
result Ensemble models achieve 0.984 accuracy, significantly outperforming baseline.

The paper examines how NFT valuations correlate with market data and social trends.

problem Predicting NFT valuations based on market data and social trends.
method Utilizes public market data, NFT metadata, and social trends data; employs linear regression and recurrent neural networks.
result Identifies correlations between NFT valuations and various features.

Optimizes real-time data processing in HFT algorithms using machine learning.

problem Optimizing data processing speed in high-frequency trading.
method Adaptive feature selection mechanism, clustering, feature weight analysis, lightweight neural networks.
result The model maintains consistent performance across varying market conditions.

Investment strategy for NYSE stocks minimizes market correlation.

problem Minimizing market correlation for steady returns.
method Combining momentum, fundamentals, and analyst recommendations; feature selection; backtesting various portfolio construction methods.
result Risk parity outperformed other methods, offering higher Sharpe ratio and lower beta.

The paper combines supervised and unsupervised learning to predict financial market movements.

problem Predicting profitable opportunities in financial markets using machine learning.
method The paper uses linear models and Gaussian Mixture Models (GMM) to extract features from Bitcoin, Pepecoin, and Nasdaq markets.
result GMM filtering improved the performance of KNN and RF algorithms, leading to higher average returns.

High Frequency Trading (HFT) represents an ever growing proportion of all financial transactions as most markets have now switched to electronic order book systems. The main goal of the paper is to propose continuous time equations which generalize the self-financing relationships of frictionless markets to electronic …

2013-12-09abs ↗pdf ↗

This study enhances sales forecasts by integrating market indicators into forecasting models.

problem Traditional forecasting models rely solely on historical demand data.
method Automated integration of macroeconomic time series data (GDP growth) into forecasting models using feature selection methods.
result Feature selection methods, especially Forward Feature Selection, significantly improve forecasting accuracy.

Study predicts soccer player market values using machine learning and SHAP for interpretability.

problem Predicting accurate market values for professional soccer players.
method Ensemble machine learning models, SHAP for interpretability, Boruta for feature selection.
result GBDT model achieved high predictive accuracy (R-squared 0.901, RMSE 3,221,632.175).

The study reveals traders' risk aversion and a new risk premium from market volumes.

problem Understanding traders' rationality and risk aversion from market volumes.
method Optimal Merton dynamics model to estimate average risk aversion and price of risk.
result Validation of the proposed trading strategy model on real data.

This paper uses deep RL to optimize market quotes from LOB data.

problem Optimizing quotes for market making from complex LOB data.
method Attn-LOB neural network with convolutional filters and attention mechanism for feature extraction; hybrid reward function for continuous action space.
result The RL agent outperforms traditional methods in market making tasks.

This study examines non-retail trading on Polymarket, revealing unique behavior patterns and structural limitations.

problem Lack of address-level quote-lifecycle data in Polymarket prediction markets.
method Empirical analysis of 13 million order-filled events using DBSCAN clustering on a six-feature fill-side vector.
result Non-retail behavior is uni-modal, contradicting previous archetypal hypotheses.

Uses news sentiment scores for direct reinforcement trading in financial markets.

problem Incorporating news data into quantitative trading remains challenging.
method Directly uses news sentiment scores and raw data as inputs for reinforcement learning, processed by sequence models.
result Achieves superior performance compared to market benchmarks.