Globally Optimized Mutual Influence Aware Ranking in E-Commerce Search

Authors: Tao Zhuang, Wenwu Ou, Zhirong Wang

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We performed online A/B test on a large e-commerce search engine. The results show that our method brings a 5% increase in GMV for the search engine over a strong baseline.
Researcher Affiliation Industry Tao Zhuang1, Wenwu Ou2, Zhirong Wang3 Taobao Search, Alibaba Group Holding Limited
Pseudocode Yes Algorithm 1 Beam search for Ranking with RNN model
Open Source Code No The paper does not provide an explicit statement or link to open-source code for the described methodology.
Open Datasets No Our training data for purchase probability estimation are from the query logs of Taobao Search.
Dataset Splits No The paper specifies a train/test split by time ('one day s log data for training and the next day s log data for test') but does not mention a distinct validation split.
Hardware Specification No The paper mentions performing 'online A/B test on Taobao Search' but does not specify any particular hardware components like CPU or GPU models used for training or inference.
Software Dependencies No The paper mentions using 'DNN', 'RNN', and 'LSTM' as model architectures but does not list any specific software dependencies with version numbers (e.g., Python, TensorFlow, PyTorch versions).
Experiment Setup Yes In mi DNN model, the sizes of the three hidden layers are 50, 50, 30. In RNN models, the hidden vector size of LSTM is 50. The sizes of ai and posi in Equation (13) are 10 and 5 respectively. The beam sizes of our RNN models are set to 5 unless stated otherwise.