Different from large-scale platforms such as Taobao and Amazon, developing CVR models in small-scale recommendation scenarios is more challenging due to the severe Data Distribution Fluctuation (DDF) issue. DDF prevents existing CVR models from being effective since 1) several months of data are needed to train CVR models sufficiently in small scenarios, leading to considerable distribution discrepancy between training and online serving; and 2) e-commerce promotions have much more significant impacts on small scenarios, leading to distribution uncertainty of the upcoming time period. In this work, we propose a novel CVR method named MetaCVR from a perspective of meta learning to address the DDF issue. Firstly, a base CVR model which consists of a Feature Representation Network (FRN) and output layers is elaborately designed and trained sufficiently with samples across months. Then we treat time periods with different data distributions as different occasions and obtain positive and negative prototypes for each occasion using the corresponding samples and the pre-trained FRN. Subsequently, a Distance Metric Network (DMN) is devised to calculate the distance metrics between each sample and all prototypes to facilitate mitigating the distribution uncertainty. At last, we develop an Ensemble Prediction Network (EPN) which incorporates the output of FRN and DMN to make the final CVR prediction. In this stage, we freeze the FRN and train the DMN and EPN with samples from recent time period, therefore effectively easing the distribution discrepancy. To the best of our knowledge, this is the first study of CVR prediction targeting the DDF issue in small-scale recommendation scenarios. Experimental results on real-world datasets validate the superiority of our MetaCVR and online A/B test also shows our model achieves impressive gains of 11.92% on PCVR and 8.64% on GMV.
In this paper, we introduce Cross-modal Alignment with mixture experts Neural Network (CameNN) recommendation model for intral-city retail industry, which aims to provide fresh foods and groceries retailing within 5 hours delivery service arising for the outbreak of Coronavirus disease (COVID-19) pandemic around the world. We propose CameNN, which is a multi-task model with three tasks including Image to Text Alignment (ITA) task, Text to Image Alignment (TIA) task and CVR prediction task. We use pre-trained BERT to generate the text embedding and pre-trained InceptionV4 to generate image patch embedding (each image is split into small patches with the same pixels and treat each patch as an image token). Softmax gating networks follow to learn the weight of each transformer expert output and choose only a subset of experts conditioned on the input. Then transformer encoder is applied as the share-bottom layer to learn all input features' shared interaction. Next, mixture of transformer experts (MoE) layer is implemented to model different aspects of tasks. At top of the MoE layer, we deploy a transformer layer for each task as task tower to learn task-specific information. On the real word intra-city dataset, experiments demonstrate CameNN outperform baselines and achieve significant improvements on the image and text representation. In practice, we applied CameNN on CVR prediction in our intra-city recommender system which is one of the leading intra-city platforms operated in China.
The rapid growth of edge data generated by mobile devices and applications deployed at the edge of the network has exacerbated the problem of information overload. As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data. The visual information in the movie trailer is a significant part of the movie recommender system. However, due to the complexity of visual information extraction, data sparsity cannot be remarkably alleviated by merely using the rough visual features to improve the rating prediction accuracy. Fortunately, the convolutional neural network can be used to extract the visual features precisely. Therefore, the end-to-end neural image caption (NIC) model can be utilized to obtain the textual information describing the visual features of movie trailers. This paper proposes a trailer inception probabilistic matrix factorization model called Ti-PMF, which combines NIC, recurrent convolutional neural network, and probabilistic matrix factorization models as the rating prediction model. We implement the proposed Ti-PMF model with extensive experiments on three real-world datasets to validate its effectiveness. The experimental results illustrate that the proposed Ti-PMF outperforms the existing ones.
To avoid serious diabetic complications, people with type 1 diabetes must keep their blood glucose levels (BGLs) as close to normal as possible. Insulin dosages and carbohydrate consumption are important considerations in managing BGLs. Since the 1960s, models have been developed to forecast blood glucose levels based on the history of BGLs, insulin dosages, carbohydrate intake, and other physiological and lifestyle factors. Such predictions can be used to alert people of impending unsafe BGLs or to control insulin flow in an artificial pancreas. In past work, we have introduced an LSTM-based approach to blood glucose level prediction aimed at "what if" scenarios, in which people could enter foods they might eat or insulin amounts they might take and then see the effect on future BGLs. In this work, we invert the "what-if" scenario and introduce a similar architecture based on chaining two LSTMs that can be trained to make either insulin or carbohydrate recommendations aimed at reaching a desired BG level in the future. Leveraging a recent state-of-the-art model for time series forecasting, we then derive a novel architecture for the same recommendation task, in which the two LSTM chain is used as a repeating block inside a deep residual architecture. Experimental evaluations using real patient data from the OhioT1DM dataset show that the new integrated architecture compares favorably with the previous LSTM-based approach, substantially outperforming the baselines. The promising results suggest that this novel approach could potentially be of practical use to people with type 1 diabetes for self-management of BGLs.
Shared-account Cross-domain Sequential recommendation (SCSR) is the task of recommending the next item based on a sequence of recorded user behaviors, where multiple users share a single account, and their behaviours are available in multiple domains. Existing work on solving SCSR mainly relies on mining sequential patterns via RNN-based models, which are not expressive enough to capture the relationships among multiple entities. Moreover, all existing algorithms try to bridge two domains via knowledge transfer in the latent space, and the explicit cross-domain graph structure is unexploited. In this work, we propose a novel graph-based solution, namely DA-GCN, to address the above challenges. Specifically, we first link users and items in each domain as a graph. Then, we devise a domain-aware graph convolution network to learn user-specific node representations. To fully account for users' domain-specific preferences on items, two novel attention mechanisms are further developed to selectively guide the message passing process. Extensive experiments on two real-world datasets are conducted to demonstrate the superiority of our DA-GCN method.
Session-based recommendation plays a central role in a wide spectrum of online applications, ranging from e-commerce to online advertising services. However, the majority of existing session-based recommendation techniques (e.g., attention-based recurrent network or graph neural network) are not well-designed for capturing the complex transition dynamics exhibited with temporally-ordered and multi-level inter-dependent relation structures. These methods largely overlook the relation hierarchy of item transitional patterns. In this paper, we propose a multi-task learning framework with Multi-level Transition Dynamics (MTD), which enables the jointly learning of intra- and inter-session item transition dynamics in automatic and hierarchical manner. Towards this end, we first develop a position-aware attention mechanism to learn item transitional regularities within individual session. Then, a graph-structured hierarchical relation encoder is proposed to explicitly capture the cross-session item transitions in the form of high-order connectivities by performing embedding propagation with the global graph context. The learning process of intra- and inter-session transition dynamics are integrated, to preserve the underlying low- and high-level item relationships in a common latent space. Extensive experiments on three real-world datasets demonstrate the superiority of MTD as compared to state-of-the-art baselines.
The effects of traffic congestion are adverse, primarily including air pollution, commuter stress, and an increase in vehicle operating costs and accidents on the road. In efforts to alleviate these problems in metropolitan cities, logistics companies plan to introduce a new method of everyday commute called air taxis, an Urban Air Mobility (UAM) service. These are electric-powered vehicles that are expected to operate in the forthcoming years by international transportation companies like Airbus, Uber, and Kitty Hawk. Since these flying taxis are emerging mode of transportation, it is necessary to provide recommendations for the initial design, implementation, and operation. This study proposes managerial insights for these upcoming services by analyzing online customer reviews and conducting an internal assessment of helicopter operations. Helicopters are similar to air taxis in regards to their operations, and therefore, customer reviews pertaining to the former can enable us to obtain insights into the strengths and weaknesses of the short-distance aviation service, in general. A four-stage sequential approach is used in this research, wherein the online reviews are mined in Stage 1, analyzed using the bigram and trigram models in Stage 2, 7S internal assessment is conducted for helicopter services in Stage 3, and managerial recommendations for air taxis are proposed in Stage 4. The insights obtained in this paper could assist any air taxi companies in providing better customer service when they venture into the market. Keywords: Air taxi; Emerging technology; Urban Air Mobility (UAM); Helicopter services; Online customer reviews; Text analytics;
E-commerce sites strive to provide users the most timely relevant information in order to reduce shopping frictions and increase customer satisfaction. Multi armed bandit models (MAB) as a type of adaptive optimization algorithms provide possible approaches for such purposes. In this paper, we analyze using three classic MAB algorithms, epsilon-greedy, Thompson sampling (TS), and upper confidence bound 1 (UCB1) for dynamic content recommendations, and walk through the process of developing these algorithms internally to solve a real world e-commerce use case. First, we analyze the three MAB algorithms using simulated purchasing datasets with non-stationary reward distributions to simulate the possible time-varying customer preferences, where the traffic allocation dynamics and the accumulative rewards of different algorithms are studied. Second, we compare the accumulative rewards of the three MAB algorithms with more than 1,000 trials using actual historical A/B test datasets. We find that the larger difference between the success rates of competing recommendations the more accumulative rewards the MAB algorithms can achieve. In addition, we find that TS shows the highest average accumulative rewards under different testing scenarios. Third, we develop a batch-updated MAB algorithm to overcome the delayed reward issue in e-commerce and enable an online content optimization on our App homepage. For a state-of-the-art comparison, a real A/B test among our batch-updated MAB algorithm, a third-party MAB solution, and the default business logic are conducted. The result shows that our batch-updated MAB algorithm outperforms the counterparts and achieves 6.13% relative click-through rate (CTR) increase and 16.1% relative conversion rate (CVR) increase compared to the default experience, and 2.9% relative CTR increase and 1.4% relative CVR increase compared to the external MAB service.
Mobile health (mHealth) information service makes healthcare management easier for users, who want to increase physical activity and improve health. However, the differences in activity preference among the individual, adherence problems, and uncertainty of future health outcomes may reduce the effect of the mHealth information service. The current health service system usually provides recommendations based on fixed exercise plans that do not satisfy the user specific needs. This paper seeks an efficient way to make physical activity recommendation decisions on physical activity promotion in personalised mHealth information service by establishing data-driven model. In this study, we propose a real-time interaction model to select the optimal exercise plan for the individual considering the time-varying characteristics in maximising the long-term health utility of the user. We construct a framework for mHealth information service system comprising a personalised AI module, which is based on the scientific knowledge about physical activity to evaluate the individual exercise performance, which may increase the awareness of the mHealth artificial intelligence system. The proposed deep reinforcement learning (DRL) methodology combining two classes of approaches to improve the learning capability for the mHealth information service system. A deep learning method is introduced to construct the hybrid neural network combing long-short term memory (LSTM) network and deep neural network (DNN) techniques to infer the individual exercise behavior from the time series data. A reinforcement learning method is applied based on the asynchronous advantage actor-critic algorithm to find the optimal policy through exploration and exploitation.