Quant

Taiwan’s short-selling signals are often misleading because the market operates under a dual-track system: retail investors short stocks through margin accounts, while institutional investors use securities borrowing and lending (SBL). Only SBL-based short selling reflects informed institutional sentiment, while margin shorting introduces noise. This study isolates SBL to construct the Short Interest Ratio (SIR) and evaluates its ability to predict cross-sectional returns and reveal size-dependent patterns in informed short-selling behavior.

In TQuant backtesting and live trading, order functions serve as the central link between strategy logic and capital management. Choosing the right order method not only makes the code cleaner and easier to read but also improves the efficiency of risk control and portfolio rebalancing. TQuant provides order functions across three dimensions — share quantity, capital amount, and portfolio weight. For each dimension, there are two variants: a basic order and a target order. In total, this gives us six order placement methods. In the following sections, we will explain the features, parameters, and recommended applications of each.

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.

Preface In financial investment, mastering accurate and comprehensive data is an indispensable skill, and effectively managing stock pools and acquiring stock price data is the key to unlocking this skill. With the tools and APIs provided by TQuant Lab, we can easily define screening criteria, quickly establish stock pools that meet specific requirements, and retrieve […]

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

This article will explore what quantitative data is, outlining its meaning, types, and examples, while briefly viewing its collection and analysis methods.

what is the right way to invest? If you’ve had the same doubts, you’re not alone. While seeking answers, I stumbled upon a term that was entirely new to me: quantitative finance. Learning this field helps resolve personal financial challenges and enhances career competitiveness. More importantly, it sharpens your logical thinking and data analysis skills—benefits that are hard to overlook. TQuant Lab provides everything you need to get started efficiently and effectively. Let’s embark on this journey together and explore the endless possibilities of quantitative trading!

This article will guide you through leveraging the TQuant Lab SuperTrend strategy in combination with the SinoPac API to quickly master the essentials of algorithmic trading. Let’s become pioneers of algorithmic trading in the Taiwan stock market together!

What is quantitative data analysis? See how numerical data is analyzed using proven methods, with examples and practical applications in finance and analytics.

In the first article—Verifying LSTM Stock Price Prediction Effectiveness Using TQuant Lab (Part 1)—we compared the predicted data with the actual data to conduct an initial evaluation of the performance of two trained models (for stocks 2618 and 8615). The results were promising. For a more detailed analysis, you can click the link above to learn more, as we will not go into further details here due to space constraints.

If you’ve been involved in investing for some time, you’ve likely heard a lot about algorithmic trading and quantitative trading strategies. For beginners with no software or coding background, it might seem daunting at first. However, with the rise of AI in recent years, the ability to automate investment strategies could become an essential tool […]

This article uses the LSTM time series model for deep learning-based LSTM stock price prediction, utilizing the opening, high, low, and closing prices of the past five days, quarterly ROE, MOM (indicating the magnitude of price trend changes, and the direction of market trends), and RSI indicators to predict the next day's closing price.