Software design in e-commerce can be improved with user data through controlled experiments (i.e. A/B tests) to better meet user needs. Machine learning-based algorithmic optimization techniques extends the approach to large number of variables to personalize software to different user needs. So far the optimization techniques has only been applied to optimize software of low complexity, such as colors and wordings of text. In this paper, we introduce the COMBO toolkit with capability to model optimization variables and their relationship constraints specified through an embedded domain-specific language. The toolkit generates personalized software configurations for users as they arrive in the system, and the configurations improve over time in in relation to some given metric. COMBO has several implementations of machine learning algorithms and constraint solvers to optimize the model with user data by software developers without deep optimization knowledge. The toolkit was validated in a proof-of-concept by implementing two features that are relevant to Apptus, an e-commerce company that develops algorithms for web shops. The algorithmic performance was evaluated in simulations with realistic historic user data. The validation shows that the toolkit approach can model and improve relatively complex features with many types of variables and constraints, without causing noticeable delays for users. We show that modeling software hierarchies in a formal model facilitates algorithmic optimization of more complex software. In this way, using COMBO, developers can make data-driven and personalized software products.

中文翻译：

---

具有面向约束的多变量 Bandit 优化 (COMBO) 的数据驱动软件设计

电子商务中的软件设计可以通过受控实验（即 A/B 测试）利用用户数据进行改进，以更好地满足用户需求。基于机器学习的算法优化技术将方法扩展到大量变量，以根据不同用户的需求个性化软件。到目前为止，优化技术仅应用于优化低复杂度的软件，例如文本的颜色和措辞。在本文中，我们介绍了 COMBO 工具包，该工具包能够对通过嵌入式领域特定语言指定的优化变量及其关系约束进行建模。当用户到达系统时，该工具包为他们生成个性化的软件配置，并且这些配置会随着时间的推移就某些给定的指标进行改进。COMBO 有多种机器学习算法和约束求解器的实现，可以由没有深入优化知识的软件开发人员使用用户数据优化模型。该工具包通过实现与 Apptus 相关的两个功能在概念验证中得到验证，Apptus 是一家为网上商店开发算法的电子商务公司。算法性能在模拟中使用真实的历史用户数据进行评估。验证表明，该工具包方法可以对具有多种类型变量和约束的相对复杂的特征进行建模和改进，而不会对用户造成明显的延迟。我们表明，在正式模型中建模软件层次结构有助于更复杂软件的算法优化。这样，使用COMBO，开发者就可以制作数据驱动的、个性化的软件产品。