Quantitative Algorithm Developer (Stock Price Prediction Model with Backtesting)
We are looking for an experienced Quantitative Algorithm Developer to design and build a robust quantitative
model that predicts stock price movements based on both actual market data and estimated/projected data.
The model should analyze historical and real-time stock data to forecast short-term and medium-term price
movements, incorporating behavioral patterns from past earnings announcements to inform future predictions.
Key Requirements
ā¢ Price Movement Prediction: Build a model that predicts stock price direction and magnitude using actual
market data and estimated/projected inputs (e.g., analyst estimates, consensus EPS/revenue forecasts).
ā¢ Earnings Event Analysis: Analyze and integrate historical earnings announcement behavior ā including
pre- and post-earnings price movements ā as a predictive factor.
ā¢ Past Behavior Integration: Factor in historical price patterns, volatility cycles, and seasonal tendencies
into the model.
ā¢ Backtesting Engine: Develop a fully functional backtesting framework to validate model performance,
including Sharpe ratio, max drawdown, win rate, and alpha generation.
ā¢ Data Pipeline: Set up or integrate with data sources (e.g., Yahoo Finance, Bloomberg, Quandl, Alpha
Vantage) for clean data ingestion.
ā¢ Documentation: Provide clear documentation of model logic, assumptions, parameters, and backtesting
results.
Preferred Skills & Experience
ā¢ Strong background in quantitative finance and algorithmic trading
ā¢ Proficiency in Python (Pandas, NumPy, scikit-learn, statsmodels, Backtrader or Zipline)
ā¢ Experience with ML or statistical models for financial time series (LSTM, XGBoost, ARIMA, factor models)
ā¢ Familiarity with earnings event studies and event-driven strategies
ā¢ Knowledge of options pricing or implied volatility is a plus
ā¢ Experience with platforms like QuantConnect, Zipline, or Backtrader
Apply Now
Apply Now
model that predicts stock price movements based on both actual market data and estimated/projected data.
The model should analyze historical and real-time stock data to forecast short-term and medium-term price
movements, incorporating behavioral patterns from past earnings announcements to inform future predictions.
Key Requirements
ā¢ Price Movement Prediction: Build a model that predicts stock price direction and magnitude using actual
market data and estimated/projected inputs (e.g., analyst estimates, consensus EPS/revenue forecasts).
ā¢ Earnings Event Analysis: Analyze and integrate historical earnings announcement behavior ā including
pre- and post-earnings price movements ā as a predictive factor.
ā¢ Past Behavior Integration: Factor in historical price patterns, volatility cycles, and seasonal tendencies
into the model.
ā¢ Backtesting Engine: Develop a fully functional backtesting framework to validate model performance,
including Sharpe ratio, max drawdown, win rate, and alpha generation.
ā¢ Data Pipeline: Set up or integrate with data sources (e.g., Yahoo Finance, Bloomberg, Quandl, Alpha
Vantage) for clean data ingestion.
ā¢ Documentation: Provide clear documentation of model logic, assumptions, parameters, and backtesting
results.
Preferred Skills & Experience
ā¢ Strong background in quantitative finance and algorithmic trading
ā¢ Proficiency in Python (Pandas, NumPy, scikit-learn, statsmodels, Backtrader or Zipline)
ā¢ Experience with ML or statistical models for financial time series (LSTM, XGBoost, ARIMA, factor models)
ā¢ Familiarity with earnings event studies and event-driven strategies
ā¢ Knowledge of options pricing or implied volatility is a plus
ā¢ Experience with platforms like QuantConnect, Zipline, or Backtrader
Apply Now
Apply Now