TQuant Lab

Analyze industry rotation between Taiwan’s shipping and semiconductor sectors using momentum and valuation factors. This study reveals how factor-based strategies capture cyclical shifts—and why semiconductors ultimately outperformed over time.

Discover how Derwood Chase’s value-momentum strategy—favoring low P/E stocks with strong price trends—delivers long-term outperformance in Taiwan’s market. Backtest results show strong alpha and lower drawdowns, proving the power of disciplined factor investing.

On June 6, 2025, the TFA International Conference had been held at NTNU with the theme “Artificial Intelligence and Finance.” TEJ had delivered a seminar, “Enhancing Factor Investing Strategy Performance Using Machine Learning,” sharing empirical research on applying quantitative methods to Taiwan’s stock market.

With the rapid development of the high-tech industry, technology stocks have increasingly become the focus of the market. While these stocks offer significant growth potential, they also come with high volatility and substantial investment risk. Investors seeking high returns may face major losses if they fail to properly assess the associated risks. Therefore, effectively measuring and managing the downside risk of high-tech stocks has become a crucial component of sound investment decision-making.

The Zipline engine, integrated within TQuant Lab, offers a high-quality and realistic backtesting framework. It leverages four core functions—initialize、handle_data、analyze、run_algorithm——to construct a comprehensive simulation environment. These components enable trading strategies to dynamically adjust to market conditions, incorporating elements such as slippage and transaction costs to ensure that backtest results closely reflect real-world performance. This article begins with a brief overview of the four key components and their applications. It then focuses in detail on the initialize function, exploring its specific configurations and role within the backtesting process.

Traditional Ichimoku strategies rely on fixed parameters (9-26-52) and visual interpretation, making them inflexible in adapting to different market conditions. XGBoost learns complex high-dimensional relationships between different data points and enhances the filtering and decision-making process of trading signals. This article use XGBoost to enhance investment performance of Ichimoku Cloud.

Dividend arbitrage focuses on the price inefficiencies between dividend payouts and option pricing. This article will explore its execution process, examples, and challenges.

Dividend arbitrage focuses on the price inefficiencies between dividend payouts and option pricing. This article will explore its execution process, examples, and challenges.

Dividend arbitrage focuses on the price inefficiencies between dividend payouts and option pricing. This article will explore its execution process, examples, and challenges.

Quantitative data collection methods include surveys, interviews, observations, and dataset reviews. Explore the techniques, pros, and cons of each method.

Dividend arbitrage focuses on the price inefficiencies between dividend payouts and option pricing. This article will explore its execution process, examples, and challenges.

This series of articles uses Alphalens to examine the application and effectiveness of various factors in the market. In previous articles, we analyzed "foreign capital factors," exploring how foreign investments influence the market. This article will focus on "value factors," examining valuation-related indicators that reveal intrinsic value and affect long-term returns. You can use the alphalens-tej tool within TQuant Lab. This tool not only integrates TEJ data but also eliminates tedious data processing, allowing you to easily assess factor performance and further support the development of investment strategies.