Quantitative analysis, from data processing and trading signal generation to portfolio management. Using machine learning to generate trading signals. Using Python to work with historical stock data, develop trading strategies, and construct a multi-factor model with optimization.
Implementing a momentum trading strategy and test if it has the potential to be profitable. Working with historical data of a given stock universe and generate a trading signal based on a momentum indicator. Computing the signal and produce projected returns. And performing a statistical test to conclude if there is alpha in the signal.
Coding and evaluating a breakout signal. Running statistical tests to test for normality and to find alpha. finding outliers and evaluating the effect that filtered outliers could have on trading signal. Running various scenarios of model with or without the outliers and decide if the outliers should be kept or not.
Creating two portfolios utilizing smart beta methodology and optimization.
Evaluating the performance of the portfolios by calculating tracking errors.
Calculating the turnover of portfolio and finding the best timing to rebalance.
Analyzing fundamental data, and by quadratic programming.
Generating multiple alpha factors. Applying various techniques to evaluate the performance of alpha factors to pick the best ones for portfolio. Formulating an advanced portfolio optimization problem by working with constraints such as risk models, leverage, market neutrality and limits on factor exposures.
Applying Natural Language Processing on corporate filings, such as 10Q and 10K statements, from cleaning data and text processing, to feature extraction and modeling. Utilizing bag-of-words and TF-IDF to generate company-specific sentiments. Based on the sentiments, deciding which company to invest in, and the optimal time to buy or sell.
Building deep neural networks to process and interpret news data. Playing with different ways of embedding words into vectors. Constructing and training LSTM networks for sentiment classification. Running backtests and apply the models to news data for signal generation.
Creating a prediction model for S&P 500 and its constituent stocks by performing model selection for a large data set which includes market data, fundamental data and alternative data. Validating model to ensure there is no overfitting. Ranking and selecting stocks to construct a long/short portfolio based on the prediction results.
Constructing open-high-low-close (OHLC) data feed and a backtesting framework. Implementing various visualization techniques for backtesting. Constructing trading strategies using various parameters such as trade days, take profit levels, stop loss levels, etc. Optimizing the parameters and evaluate the performance by analyzing the results of backtests.