Department of Computer Science and Engineering, Hanyang University, Seoul, South Korea.
PLoS One. 2020 Jun 5;15(6):e0232887. doi: 10.1371/journal.pone.0232887. eCollection 2020.
In the field of advertising technology, it is a key task to forecast posterior click distribution since 66% of advertising transactions depend on cost per click model. However, due to the General Data Protection Regulation, machine learning techniques to forecast posterior click distribution based on the sequences of an identified user's actions are restricted in European countries. To overcome this barrier, we introduce a contextual behavior concept for the advertising network environment and propose a new hybrid model, which we call the Long Short Term Memory-Hawkes model by combining a stochastic-based generative model and a machine learning-based predictive model. Also, to meet the computational efficiency for the heavy demand in mobile advertisement market, we define gradient exponential kernel with just three hyper parameters to minimize residuals. We have carefully tested our proposed model with production data and found that the LSTM-Hawkes model reduces the Mean Squared Error by at least 27.1% and up to 83.8% on average in comparison to the existing Hawkes Process based algorithm, Hawkes Intensity Process, as well as 39.77% on average in comparison to Multivariate Linear Regression. We have also found that our proposed model improves the forecast accuracy by about 21.2% on average.
在广告技术领域，预测后续点击分布是一项关键任务，因为 66%的广告交易都依赖于点击付费模型。然而，由于通用数据保护条例的限制，基于已识别用户行为序列的机器学习技术在欧洲国家受到限制，无法用于预测后续点击分布。为了克服这一障碍，我们引入了一个广告网络环境中的上下文行为概念，并提出了一种新的混合模型，我们称之为基于长短时记忆的 Hawkes 模型，它结合了基于随机的生成模型和基于机器学习的预测模型。此外，为了满足移动广告市场的高需求的计算效率，我们定义了具有三个超参数的梯度指数核，以最小化残差。我们使用生产数据对所提出的模型进行了仔细的测试，发现与现有的基于 Hawkes 过程的算法 Hawkes Intensity Process 相比，LSTM-Hawkes 模型至少将均方误差降低了 27.1%，平均降低了 83.8%，与多元线性回归相比，平均降低了 39.77%。我们还发现，与现有的 Hawkes 过程的算法 Hawkes Intensity Process 相比，我们的模型将预测准确性提高了约 21.2%。
