# Ceruleanacg/Personae

📈 Personae is a repo of implements and environment of Deep Reinforcement Learning & Supervised Learning for Quantitative Trading.

Repository: https://github.com/Ceruleanacg/Personae
Canonical: https://ross.abutalabs.com/products/personae
Language: Python
License: MIT
License Family: permissive
Topics: reinforcement-learning, supervised-learning, stock-data, trading, paper, stock, time-series-prediction, stock-price-prediction
Last push: 2018-11-29T17:06:12+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3098, "days_push": 2834, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1407, forks 342 (observed 2026-08-28T04:04:38.470746+00:00)

## What it is
Personae is a Python library implementing deep reinforcement learning (DDPG, Double DQN, Dueling DQN, Policy Gradient) and supervised learning (DA-RNN, TreNet, LSTM) algorithms with TensorFlow for quantitative trading research. It includes a simulated financial market environment supporting stocks and futures that serves as a gym-style environment for training and evaluating these models.

## Use cases
- apply deep reinforcement learning to stock trading
- predict stock prices with LSTM or attention RNN models
- simulate a financial market environment for trading agents
- reproduce RL trading papers like DDPG and Double DQN
- experiment with supervised learning for time series prediction in finance
- backtest trading strategies with neural network models

## When to choose
- you want reference TensorFlow implementations of RL algorithms applied to trading
- you need a simple simulated market environment for stock or futures experiments
- you are doing research or coursework on deep RL for quantitative finance
- you want paper-faithful implementations of DA-RNN, TreNet, or DQN variants

## When to avoid
- you need production-ready trading infrastructure or live broker integration
- you require high-frequency or intraday data - only day frequency is supported
- you want well-maintained software - the repo was under reconstruction and development has stalled
- you need sophisticated feature engineering - the included features are explicitly naive

## Facets
- artifact type: library
- maturity: maintenance
- function: reinforcement-learning, machine-learning, trading, simulation
- domain: reinforcement-learning, machine-learning, fintech, time-series
- platform: python
- tags: quantitative-trading, tensorflow, stock-prediction, gym-environment, ddpg, dqn, lstm, time-series-prediction, docker

## Member repositories
- Ceruleanacg/Personae (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:38.470746+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:38:37.070004+00:00, confidence not recorded.
  - readme: https://github.com/Ceruleanacg/Personae (fetched 2026-08-28T04:04:38.470746+00:00, sha b6edbc388f6e)
- Data as of 2026-08-30T08:39:29.467469+00:00.