scholarly journals Deep Time-Stream Framework for Click-through Rate Prediction by Tracking Interest Evolution

2020 ◽  
Vol 34 (04) ◽  
pp. 5726-5733
Author(s):  
Shu-Ting Shi ◽  
Wenhao Zheng ◽  
Jun Tang ◽  
Qing-Guo Chen ◽  
Yao Hu ◽  
...  
Keyword(s):  
Continuous Time ◽  
Industrial Applications ◽  
Superior Performance ◽  
User Interest ◽  
Additional Time ◽  
Deep Time ◽  
Public Dataset ◽  
Click Through Rate ◽  
Time Information ◽  
Video Recommendation

Click-through rate (CTR) prediction is an essential task in industrial applications such as video recommendation. Recently, deep learning models have been proposed to learn the representation of users' overall interests, while ignoring the fact that interests may dynamically change over time. We argue that it is necessary to consider the continuous-time information in CTR models to track user interest trend from rich historical behaviors. In this paper, we propose a novel Deep Time-Stream framework (DTS) which introduces the time information by an ordinary differential equations (ODE). DTS continuously models the evolution of interests using a neural network, and thus is able to tackle the challenge of dynamically representing users' interests based on their historical behaviors. In addition, our framework can be seamlessly applied to any existing deep CTR models by leveraging the additional Time-Stream Module, while no changes are made to the original CTR models. Experiments on public dataset as well as real industry dataset with billions of samples demonstrate the effectiveness of proposed approaches, which achieve superior performance compared with existing methods.

A Collaborative Filtering Recommendation Algorithm Incorporated with Life Cycle

2013 ◽  
Vol 765-767 ◽  
pp. 630-633 ◽  
Author(s):  
Chong Lin Zheng ◽  
Kuang Rong Hao ◽  
Yong Sheng Ding
Keyword(s):  
Life Cycle ◽  
Collaborative Filtering ◽  
Recommendation Systems ◽  
Experimental Results ◽  
User Interest ◽  
Recommendation Algorithm ◽  
Time Information ◽  
Successful Technology

Collaborative filtering recommendation algorithm is the most successful technology for recommendation systems. However, traditional collaborative filtering recommendation algorithm does not consider the change of time information. For this problem,this paper improve the algorithm with two new methods:Predict score incorporated with time information in order to reflect the user interest change; Recommend according to scores by adding the weight information determined by the item life cycle. Experimental results show that the proposed algorithm outperforms the traditional item in accuracy.

A Video Recommendation Algorithm Based on Hyperlink-Graph Model

2017 ◽  
Vol 5 (3) ◽  
pp. 49-63
Author(s):  
Songtao Shang ◽  
Wenqian Shang ◽  
Minyong Shi ◽  
Shuchao Feng ◽  
Zhiguo Hong
Keyword(s):  
Graph Model ◽  
User Interest ◽  
Recommendation Algorithm ◽  
Internet Users ◽  
Recommendation Algorithms ◽  
The Matrix ◽  
Personal Recommendation ◽  
Low Efficiency ◽  
Sports Videos ◽  
Video Recommendation

The traditional graph-based personal recommendation algorithms mainly depend the user-item model to construct a bipartite graph. However, the traditional algorithms have low efficiency, because the matrix of the algorithms is sparse and it cost lots of time to compute the similarity between users or items. Therefore, this paper proposes an improved video recommendation algorithm based on hyperlink-graph model. This method cannot only improve the accuracy of the recommendation algorithms, but also reduce the running time. Furthermore, the Internet users may have different interests, for example, a user interest in watching news videos, and at the same time he or she also enjoy watching economic and sports videos. This paper proposes a complement algorithm based on hyperlink-graph for video recommendations. This algorithm improves the accuracy of video recommendations by cross clustering in user layers.

scholarly journals Deep Session Interest Network for Click-Through Rate Prediction

2019 ◽  
Author(s):  
Yufei Feng ◽  
Fuyu Lv ◽  
Weichen Shen ◽  
Menghan Wang ◽  
Fei Sun ◽  
...  
Keyword(s):  
Recommender Systems ◽  
Target Item ◽  
State Of The Art ◽  
Online Advertising ◽  
Industrial Applications ◽  
Research Topic ◽  
Intrinsic Structure ◽  
User Behaviors ◽  
Click Through Rate ◽  
Behavior Sequences

Click-Through Rate (CTR) prediction plays an important role in many industrial applications, such as online advertising and recommender systems. How to capture users' dynamic and evolving interests from their behavior sequences remains a continuous research topic in the CTR prediction. However, most existing studies overlook the intrinsic structure of the sequences: the sequences are composed of sessions, where sessions are user behaviors separated by their occurring time. We observe that user behaviors are highly homogeneous in each session, and heterogeneous cross sessions. Based on this observation, we propose a novel CTR model named Deep Session Interest Network (DSIN) that leverages users' multiple historical sessions in their behavior sequences. We first use self-attention mechanism with bias encoding to extract users' interests in each session. Then we apply Bi-LSTM to model how users' interests evolve and interact among sessions. Finally, we employ the local activation unit to adaptively learn the influences of various session interests on the target item. Experiments are conducted on both advertising and production recommender datasets and DSIN outperforms other state-of-the-art models on both datasets.

scholarly journals Influence prediction for continuous-time information propagation on networks

2018 ◽  
Vol 13 (4) ◽  
pp. 567-583 ◽  
Author(s):  
Shui-Nee Chow ◽  
◽  
Xiaojing Ye ◽  
Hongyuan Zha ◽  
Haomin Zhou ◽  
...  
Keyword(s):  
Continuous Time ◽  
Information Propagation ◽  
Time Information

Dynamic user modeling for expert recommendation in community question answering

2020 ◽  
Vol 39 (5) ◽  
pp. 7281-7292
Author(s):  
Tongze He ◽  
Caili Guo ◽  
Yunfei Chu ◽  
Yang Yang ◽  
Yanjun Wang
Keyword(s):  
Real World ◽  
Large Scale ◽  
Question Answering ◽  
Dynamic Change ◽  
Superior Performance ◽  
User Interest ◽  
Short Term ◽  
Expert Recommendation ◽  
Community Question Answering ◽  
User Expertise

Community Question Answering (CQA) websites has become an important channel for people to acquire knowledge. In CQA, one key issue is to recommend users with high expertise and willingness to answer the given questions, i.e., expert recommendation. However, a lot of existing methods consider the expert recommendation problem in a static context, ignoring that the real-world CQA websites are dynamic, with users’ interest and expertise changing over time. Although some methods that utilize time information have been proposed, their performance improvement can be limited due to fact that they fail they fail to consider the dynamic change of both user interests and expertise. To solve these problems, we propose a deep learning based framework for expert recommendation to exploit user interest and expertise in a dynamic environment. For user interest, we leverage Long Short-Term Memory (LSTM) to model user’s short-term interest so as to capture the dynamic change of users’ interests. For user expertise, we design user expertise network, which leverages feedback on users’ historical behavior to estimate their expertise on new question. We propose two methods in user expertise network according to whether the dynamic property of expertise is considered. The experimental results on a large-scale dataset from a real-world CQA site demonstrate the superior performance of our method.

Feedforward Input Generation Based on Neural Network Prediction in Multi-Joint Robots1

2014 ◽  
Vol 136 (3) ◽  
Author(s):  
Jonathan Asensio ◽  
Wenjie Chen ◽  
Masayoshi Tomizuka
Keyword(s):  
Neural Network ◽  
Feedforward Control ◽  
Industrial Robot ◽  
Tracking Error ◽  
Industrial Applications ◽  
Superior Performance ◽  
Control Scheme ◽  
Neural Network Prediction ◽  
Network Prediction ◽  
Learning Data

Learning feedforward control based on the available dynamic/kinematic system model and sensor information is generally effective for reducing the tracking error for a learned trajectory. For new trajectories, however, the system cannot benefit from previous learning data and it has to go through the learning process again to regain its performance. In industrial applications, this means production line has to stop for learning, and the overall productivity of the process is compromised. To solve this problem, this paper proposes a feedforward input generation scheme based on neural network (NN) prediction. Learning/training is performed for the NNs for a set of trajectories in advance. Then the feedforward torque input for any trajectory in the predefined workspace can be calculated according to the predicted error from multiple NNs managed with expert logic. Experimental study on a 6-DOF industrial robot has shown the superior performance of the proposed NN based feedforward control scheme in the position tracking as well as the residual vibration reduction, without any further learning or end-effector sensors during operation.

Sign in / Sign up

Export Citation Format

Share Document