[Link]deep_portfolo - Use Reforcemet earg ad Supervsed learg to Optmze portfolo allocato []

Overview

rl_portfolio

This Repository uses Reinforcement Learning and Supervised learning to Optimize portfolio allocation. The goal is to make profitable agent which can optimize portfolio between n stocks (or any assets) by taking there price series data and output holdings in each. Portfolio can be long-short.

#How it works: In the start, I will be using episode length of one day and price series data for last n days for each stock. Time stamp will be per minute for both input and output.Mostly stock will be from same sector to start with so algo can also find some covariance among them. Idea in the end is to trade different assets and make a balanced online optimized portfolio.

#More Detailed Explanation of Algorithm: a) Make LSTM network for each asset and predict next interval price. All these networks are trained individually and trained network parameter is stored. (Code inside supervised learning)

b) Use trained LSTM networks and with other layer combine the network and start training network using Reinforcement learning so second network predict allocation to each.

#Other thoughts on the project are: a) Most of the financial engineering is about predicting the next price interval of the underlying asset. If you see first part that's what algorithm do it takes a supervised learning (made using LSTM) to predict that. This part can be separately optimised and made better in future. The more better it become the more better the algo will able to make portfolio.
b) Second part making a portfolio using RL: This part takes input from first part and log returns of the price series to predict portfolio allocation. Idea here is that even knowing next price interval doesn't guarantee much, unless you can make a portfolio of different assets which can have less drawdown and consistent returns.

Here, Idea is to make automatic optimisation algorithm based on how we set rewards. For example:

  1. Make a portfolio where I only care about returns: Just set the reward based on returns, Network will output algorithm which only trying to optimise returns.

  2. Make a portfolio where drawdown should be less and medium returns, in this case rewards will be functions which will use drawdown also to give feedback to the network. The portfolio made will be focussing on drawdown also. The brief idea is to make algorithm which can be improved everyday and so much general purpose that it can do based on what we want.

#Finding which network can explore: a) Automatic finding of look_back period for momentum strategy.
b) Automatic finding of average period of mean reverting strategy.
c) Optimize portfolio to autocorrect above.

Owner
Deepender Singla
Works at @niveshi. Before @accredible. Simple and nice guy.
Deepender Singla
A universal memory dumper using Frida

Fridump Fridump (v0.1) is an open source memory dumping tool, primarily aimed to penetration testers and developers. Fridump is using the Frida framew

551 Jan 07, 2023
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

Welcome to AirSim AirSim is a simulator for drones, cars and more, built on Unreal Engine (we now also have an experimental Unity release). It is open

Microsoft 13.8k Jan 05, 2023
GPT, but made only out of gMLPs

GPT - gMLP This repository will attempt to crack long context autoregressive language modeling (GPT) using variations of gMLPs. Specifically, it will

Phil Wang 80 Dec 01, 2022
Code for EMNLP'21 paper "Types of Out-of-Distribution Texts and How to Detect Them"

ood-text-emnlp Code for EMNLP'21 paper "Types of Out-of-Distribution Texts and How to Detect Them" Files fine_tune.py is used to finetune the GPT-2 mo

Udit Arora 19 Oct 28, 2022
Interactive web apps created using geemap and streamlit

geemap-apps Introduction This repo demostrates how to build a multi-page Earth Engine App using streamlit and geemap. You can deploy the app on variou

Qiusheng Wu 27 Dec 23, 2022
PEPit is a package enabling computer-assisted worst-case analyses of first-order optimization methods.

PEPit: Performance Estimation in Python This open source Python library provides a generic way to use PEP framework in Python. Performance estimation

Baptiste 53 Nov 16, 2022
HyperDict - Self linked dictionary in Python

Hyper Dictionary Advanced python dictionary(hash-table), which can link it-self

8 Feb 06, 2022
An SMPC companion library for Syft

SyMPC A library that extends PySyft with SMPC support SyMPC /ˈsɪmpəθi/ is a library which extends PySyft ≥0.3 with SMPC support. It allows computing o

Arturo Marquez Flores 0 Oct 13, 2021
Python package for downloading ECMWF reanalysis data and converting it into a time series format.

ecmwf_models Readers and converters for data from the ECMWF reanalysis models. Written in Python. Works great in combination with pytesmo. Citation If

TU Wien - Department of Geodesy and Geoinformation 31 Dec 26, 2022
Realtime YOLO Monster Detection With Non Maximum Supression

Realtime-YOLO-Monster-Detection-With-Non-Maximum-Supression Table of Contents In

5 Oct 07, 2022
Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics.

Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics. By Andres Milioto @ University of Bonn. (for the new P

Photogrammetry & Robotics Bonn 314 Dec 30, 2022
Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

Readme File for "Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis" by Ham, Imai, and Janson. (2022) All scripts were written and

0 Jan 27, 2022
The Ludii general game system, developed as part of the ERC-funded Digital Ludeme Project.

The Ludii General Game System Ludii is a general game system being developed as part of the ERC-funded Digital Ludeme Project (DLP). This repository h

Digital Ludeme Project 50 Jan 04, 2023
A PyTorch implementation of deep-learning-based registration

DiffuseMorph Implementation A PyTorch implementation of deep-learning-based registration. Requirements OS : Ubuntu / Windows Python 3.6 PyTorch 1.4.0

24 Jan 03, 2023
RITA is a family of autoregressive protein models, developed by LightOn in collaboration with the OATML group at Oxford and the Debora Marks Lab at Harvard.

RITA: a Study on Scaling Up Generative Protein Sequence Models RITA is a family of autoregressive protein models, developed by a collaboration of Ligh

LightOn 69 Dec 22, 2022
Code that accompanies the paper Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance

Semi-supervised Deep Kernel Learning This is the code that accompanies the paper Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data

58 Oct 26, 2022
통일된 DataScience 폴더 구조 제공 및 가상환경 작업의 부담감 해소

Lucas coded by linux shell 목차 Mac버전 CookieCutter (autoenv) 1.How to Install autoenv 2.폴더 진입 시, activate 구현하기 3.폴더 탈출 시, deactivate 구현하기 4.Alias 설정하기 5

ello 3 Feb 21, 2022
Unsupervised Feature Loss (UFLoss) for High Fidelity Deep learning (DL)-based reconstruction

Unsupervised Feature Loss (UFLoss) for High Fidelity Deep learning (DL)-based reconstruction Official github repository for the paper High Fidelity De

28 Dec 16, 2022
Easy-to-use library to boost AI inference leveraging state-of-the-art optimization techniques.

NEW RELEASE How Nebullvm Works • Tutorials • Benchmarks • Installation • Get Started • Optimization Examples Discord | Website | LinkedIn | Twitter Ne

Nebuly 1.7k Dec 31, 2022
Improving Deep Network Debuggability via Sparse Decision Layers

Improving Deep Network Debuggability via Sparse Decision Layers This repository contains the code for our paper: Leveraging Sparse Linear Layers for D

Madry Lab 35 Nov 14, 2022