Athena

Portfolio optimization is the process of selecting the best portfolio (asset distribution), out of the set of all portfolios being considered, according to some objective. The objective typically maximizes factors such as expected return, and minimizes costs like financial risk.

Investors want to gain maximum returns from their portfolio while minimizing the risks associated. But purchasing assets without analyzing the fundamentals and merely relying on speculation and market sentiment is a significant problem in portfolio management. This is the problem that the model is trying to solve so that investors can get suggestions from the model and invest wisely.

We intend to propose a novel solution to optimize and enhance portfolio performance using a combination of deep learning and statistical models along with asset fundamentals analysis to obtain maximum returns with minimal risk.

Uses

The proposed model can be used to maximize the returns and minimize the risk of a given portfolio (a collection of stocks and other assets) by allocating an optimal weight for each asset in the portfolio.
It can provide a portfolio that delivers high return per unit risk.
It can also create a balanced portfolio with many different investments such as stocks, bonds and mutual funds.

Athena is the only tool that you will ever need to optimize your portfolio.

Related tags

Overview

Athena

Uses

Model architecture

Reference Links

Site links

YouTube links

Owner

Indrajit

A cross-document event and entity coreference resolution system, trained and evaluated on the ECB+ corpus.

Official implementation of Deep Convolutional Dictionary Learning for Image Denoising.

Fine-grained Post-training for Improving Retrieval-based Dialogue Systems - NAACL 2021

Pyramid Pooling Transformer for Scene Understanding

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).

Realtime_Multi-Person_Pose_Estimation

[ICCV2021] Learning to Track Objects from Unlabeled Videos

A framework for joint super-resolution and image synthesis, without requiring real training data

Denoising Diffusion Probabilistic Models

ESGD-M - A stochastic non-convex second order optimizer, suitable for training deep learning models, for PyTorch

Eye-Blink-Counter - Python based Computer Vision project which counts how many time a person blinks

A universal framework for learning timestamp-level representations of time series

Code for "Adversarial Training for a Hybrid Approach to Aspect-Based Sentiment Analysis

Image restoration with neural networks but without learning.

Implementation of paper "DCS-Net: Deep Complex Subtractive Neural Network for Monaural Speech Enhancement"

Tree Nested PyTorch Tensor Lib

Public scripts, services, and configuration for running a smart home K3S network cluster

Empowering journalists and whistleblowers

Improving Query Representations for DenseRetrieval with Pseudo Relevance Feedback:A Reproducibility Study.