3260 papers • 126 benchmarks • 313 datasets
Portfolio management is the task of obtaining higher excess returns through the flexible allocation of asset weights. In reality, common examples are stock selection and the Enhanced Index Fund (EIF). The general solution of portfolio management is to score the potential of assets, buy assets with upside potential and increase their weighting, and sell assets that are likely to fall or are relatively weak. A large number of strategies have been proposed for portfolio management.
(Image credit: Papersgraph)
These leaderboards are used to track progress in portfolio-optimization-3
No benchmarks available.
Use these libraries to find portfolio-optimization-3 models and implementations
No datasets available.
No subtasks available.
A financial-model-free Reinforcement Learning framework to provide a deep machine learning solution to the portfolio management problem, able to achieve at least 4-fold returns in 50 days.
This work applies LSTM recurrent neural networks (RNN) in predicting the stock price correlation coefficient of two individual stocks using the ARIMA-LSTM hybrid model, which turned out superior to all other financial models by a significant scale.
In this paper, the stock future prices are predicted using Support Vector Regression and the predicted prices are used to recommend which portions of the budget an investor should invest in different existing stocks to have an optimum expected profit considering their level of risk tolerance.
A framework that bypasses traditional forecasting steps and allows portfolio weights to be optimized by updating model parameters is presented and delivers good performance under transaction costs, and a detailed study shows the rationality of their approach during the crisis.
By training a low-dimensional surrogate model end-to-end, and jointly with the predictive model, this work achieves a large reduction in training and inference time and improved performance by focusing attention on the more important variables in the optimization and learning in a smoother space.
Qlib is a bridge between AI technologies and quantitative investment that aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment.
A heuristic algorithm based on the alternating direction method of multipliers (ADMM) that allows for solve times in tens to hundreds of milliseconds with around 1000 securities and 100 risk factors is proposed and a bound on the achievable performance is obtained.
This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks through penalizing the optimization problem in its dual formulation and reducing it to a finite dimensional one which corresponds to optimizing a neural network with smooth objective function.
Adding a benchmark result helps the community track progress.