Dynamic Pricing for online retail has been discussed extensively in literature. However, past solutions fell short of addressing the unique challenges of independent multi-retailer platforms for grocery delivery. From limited visibility of retailers' inventories to diverse demand-side dynamics across retail brands and locations, the highly decentralized nature of multi-retailer platforms deviates from the classical framework of modeling price elasticity and cross-elasticity of demand. In this paper, we present a novel scheme to scalable and practical price adjustment in the highly dynamic multi-retailer context. First, we present a deep learning framework to distinctly model complex cross-elasticity relationships via additive neural networks augmented with adversarial data. Second, we present evolutionary optimization agents for adjusting itemized prices in a location-decentralized manner, while adhering to custom business constraints and objectives. The optimization utilizes the genetic algorithm structure, where we introduce a potential mechanism, inspired by bandit algorithms, in order to improve convergence speed by managing exploitation and exploration trade-offs. Our solution is deployed at Shipt and is extendable to other types of multi-retailer platforms, such as restaurant delivery. Finally, we empirically demonstrate performance using public and industry datasets of hundreds and thousands of diverse products across tens of stores, offering an optimization targets coverage scale in the tens of thousands, far larger than experimental setups in past research.

In conventional database access control models, access control policies are explicitly specified for each role against each data object. In large-scale content-centric data sharing, it might be difficult to explicitly identify accessible records for each role/user, especially when the semantic content of data is expected to play a role in access decisions. As a result, users are often over-privileged, and ex post facto auditing is enforced to detect misuse of the privileges. Unfortunately, it is usually difficult to reverse the damage, as (large amount of) data has been disclosed already. In this paper, we introduce Content-Based Access Control (CBAC), an innovative access control model for content-centric information sharing. CBAC is expected to be deployed on top of Role-Based Access Control (RBAC) or Multi-level Security (MLS), in the application scenarios where RBAC and MLS will give excessive access rights. As a complement to conventional access control models, the CBAC model makes access control decisions based on the content similarity. In CBAC, each user is allowed by an MLS or RBAC rule to access a large set of data objects, while the CBAC rule imposes an additional layer of restrictions that the user could only access “a subset” of the designated records. The boundary of the subset is dynamically determined by the textual content of data objects. We then present an enforcement mechanism for CBAC that exploits Oracle's Virtual Private Database (VPD). To further improve the performance of the proposed approach, we introduce a content-based blocking mechanism to improve the efficiency of CBAC enforcement. We also develop a content annotation mechanism for more accurate textual content matching for short text snippets. Experimental results show that CBAC makes reasonable access control decisions with a small overhead.

The classification with instances which can be tagged with any of the 2Lpossible subsets from the predefined L labels is called multi-label classification. Multi-label classification is commonly applied in domains, such as multimedia, text, web and biological data analysis. The main challenge lying in multi-label classification is the dilemma of optimising label correlations over exponentially large label powerset and the ignorance of label correlations using binary relevance strategy (1-vs-all heuristic). The classification with label powerset usually encounters with highly skewed data distribution, called imbalanced problem. While binary relevance strategy reduces the problem from exponential to linear, it totally neglects the label correlations. In this artical, we propose a novel strategy of introducing Balanced Pseudo-Labels (BPL) which build more robust classifiers for imbalanced multi-label classification, which embeds imbalanced data in the problems innately. By incorporating the new balanced labels we aim to increase the average distances among the distinct label vectors. In this way, we also code the label correlation implicitly in the algorithm. Another advantage of the proposed method is that it can combined with any classifier and it is proportional to linear label transformation. In the experiment, we choose five multi-label benchmark data sets and compare our algorithm with the most state-of-art algorithms. Our algorithm outperforms them in standard multi-label evaluation in most scenarios.

Conventional database access control models have difficulties in dealing with big data, especially for the features of volume, variety and velocity. To address the problem, we introduce the Content-based Access Control (CBAC) model for content-centric information sharing. As a complement to conventional models, CBAC makes access control decisions based on the content similarity between user credentials and data content dynamically. We present an enforcement mechanism for CBAC exploiting Oracle's Virtual Private Database (VPD). Experimental results show that CBAC makes reasonable access control decision with a small overhead.

Non-stationary Dynamic Bayesian Networks (Non-stationary DBNs) are widely used to model the temporal changes of directed dependency structures from multivariate time series data. However, the existing change-points based non-stationary DBNs methods have several drawbacks including excessive computational cost, and low convergence speed. In this paper we proposed a novel non-stationary DBNs method. Our method is based on the perfect simulation model. We applied this approach for network structure inference from synthetic data and biological microarray gene expression data and compared it with other two state-of-the-art non-stationary DBNs methods. The experimental results demonstrated that our method outperformed two other state-of-the-art methods in both computational cost and structure prediction accuracy. The further sensitivity analysis showed that once converged our model is robust to large parameter ranges, which reduces the uncertainty of the model behavior.

Visual surveillance produces large amounts of video data. Effective indexing and retrieval from surveillance video databases are very important. Although there are many ways to represent the content of video clips in current video retrieval algorithms, there still exists a semantic gap between users and retrieval systems. Visual surveillance systems supply a platform for investigating semantic-based video retrieval. In this paper, a semantic-based video retrieval framework for visual surveillance is proposed. A cluster-based tracking algorithm is developed to acquire motion trajectories. The trajectories are then clustered hierarchically using the spatial and temporal information, to learn activity models. A hierarchical structure of semantic indexing and retrieval of object activities, where each individual activity automatically inherits all the semantic descriptions of the activity model to which it belongs, is proposed for accessing video clips and individual objects at the semantic level. The proposed retrieval framework supports various queries including queries by keywords, multiple object queries, and queries by sketch. For multiple object queries, succession and simultaneity restrictions, together with depth and breadth first orders, are considered. For sketch-based queries, a method for matching trajectories drawn by users to spatial trajectories is proposed. The effectiveness and efficiency of our framework are tested in a crowded traffic scene.