LSTM Response Models for Direct Marketing Analytics: Replacing Feature Engineering with Deep Learning
LSTM Response Models for Direct Marketing Analytics: Replacing Feature Engineering with Deep Learning
复制标题
DOI：
10.1016/j.intmar.2020.07.002
复制
发表时间：
2020-05
影响因子：
11.8
通讯作者：
Mainak Sarkar;Arnaud De Bruyn
中科院分区：
文献类型：
--
作者：
Mainak Sarkar;Arnaud De Bruyn
在预测建模中，公司经常处理跨越多个渠道、网站、人口统计、购买类型和产品类别的高维数据。传统的客户响应模型在很大程度上依赖于特征工程，其性能取决于分析师的领域知识和专业知识来制作相关的预测器。然而，随着数据复杂性的增加，传统模型的复杂性呈指数级增长。在本文中，我们证明了长短期记忆（LSTM）神经网络，它完全依赖于原始数据作为输入，可以非常准确地预测客户行为。在我们的第一个应用程序中，模型优于标准基准。在第二个更现实的应用程序中，LSTM模型与271个手工制作的模型竞争，这些模型使用各种各样的特征和建模方法。它击败了其中的269个，大多数都是大幅领先。LSTM神经网络是在复杂环境中使用面板数据建模客户行为的绝佳候选者（例如，直接营销、品牌选择、点击流数据、流失预测）。
In predictive modeling, firms often deal with high-dimensional data that span multiple channels, websites, demographics, purchase types, and product categories. Traditional customer response models rely heavily on feature engineering, and their performance depends on the analyst's domain knowledge and expertise to craft relevant predictors. As the complexity of data increases, however, traditional models grow exponentially complicated. In this paper, we demonstrate that long-short term memory (LSTM) neural networks, which rely exclusively on raw data as input, can predict customer behaviors with great accuracy. In our first application, a model outperforms standard benchmarks. In a second, more realistic application, an LSTM model competes against 271 hand-crafted models that use a wide variety of features and modeling approaches. It beats 269 of them, most by a wide margin. LSTM neural networks are excellent candidates for modeling customer behavior using panel data in complex environments (e.g., direct marketing, brand choices, clickstream data, churn prediction).