Location-Aware Real-Time Recommender Systems for Brick-and-Mortar Retailers

Providing real-time product recommendations based on consumer profiles and purchase history is a successful marketing strategy in online retailing. However, brick-and-mortar (BAM) retailers have yet to utilize this important promotional strategy because it is difficult to predict consumer preferences as they travel in a physical space but remain anonymous and unidentifiable until checkout. In this paper, we develop such a recommender approach by leveraging the consumer shopping path information generated by radio frequency identification technologies. The system relies on spatial-temporal pattern discovery that measures the similarity between paths and recommends products based on measured similarity. We use a real-world retail data set to demonstrate the feasibility of this real-time recommender system and show that our approach outperforms benchmark methods in key recommendation metrics. Conceptually, this research provides generalizable insights on the correlation between spatial movement and consumer preference. It makes a strong case that the emerging location and path data and the spatial-temporal pattern discovery methods can be effectively utilized for implementable marketing strategies. Managerially, it provides one of the first real-time recommender systems for BAM retailers. Our approach can potentially become the core of the next-generation intelligent shopping environment in which the stores customize marketing efforts to provide real-time, location-aware recommendations.

Evaluating the performance of Temporal Pattern Discovery: New application using Statins and Rhabdomyolysis in OMOP databases

Background: Temporal Pattern Discovery (TPD) is a method of signal detection using electronic healthcare databases, serving as an alternative to spontaneous reporting of adverse drug events. Here, we aimed to replicate and optimise a TPD approach previously used to assess temporal signals of statins with rhabdomyolysis (in The Health Improvement Network (THIN) database) by using the OHDSI tools designed for OMOP data sources. Methods: We used data from the Truven MarketScan US Commercial Claims and the Commercial Claims and Encounters (CCAE). Using an extension of the OHDSI ICTemporalPatternDiscovery package, we ran positive and negative controls through four analytical settings and calculated sensitivity, specificity, bias and AUC to assess performance. Results: Similar to previous findings, we noted an increase in the information component (IC) for simvastatin and rhabdomyolysis following initial exposure and throughout the surveillance window. For example, the change in IC was 0.266 for the surveillance period of 1-30 days as compared to the control period of -180 to -1days. Our modification of the existing OHDSI software allowed for faster queries and more efficient generation of chronographs. Conclusion: Our OMOP replication matched the results of the original THIN study, only simvastatin had a signal. The TPD method is a useful signal detection tool that provides a single statistic on temporal association and a graphical depiction of the temporal pattern of the drug outcome combination. It remains unclear if the method works well for rare adverse events, but it has been shown to be a useful risk identification tool for longitudinal observational databases. Future work should compare the performance of TPD with other pharmacoepidemiology methods and mining techniques of signal detection. In addition, it would be worth investigating the relative TPD performance characteristics using a variety of observational data sources.

Comparative Study of Clustering Approaches Applied to Spatial or Temporal Pattern Discovery

Many clustering approaches succeed in pattern segmentation in many applications. This unsupervised segmentation should be effective to reduce an expert labelling time: i.e, they must be able to detect the number of patterns and identify them in a sequence or map with the right cuts. Several direct and hierarchical clustering approaches are compared for this task. A divisive spectral clustering architecture with a no-cut criteria is also proposed. This new algorithm achieves promise segmentation of spatial UCI databases and marine time series compared to other approaches.

Evaluating the performance of Temporal Pattern Discovery: New application using Statins and Rhabdomyolysis in OMOP databases

Introduction Temporal Pattern Discovery (TPD) is a method of signal detection using electronic healthcare databases, serving as an alternative to spontaneous reporting of adverse drug events. Here, we aimed to replicate and optimise a TPD approach previously used to assess temporal signals of statins with rhabdomyolysis (in The Health Improvement Network (THIN) database) by using the OHDSI tools designed for OMOP data sources.Methods We used data from the Truven MarketScan US Commercial Claims and the Commercial Claims and Encounters (CCAE). Using an extension of the OHDSI ICTemporalPatternDiscovery package, we ran positive and negative controls through four analytical settings and calculated sensitivity, specificity, bias and AUC to assess performance.Results Similar to previous findings, we noted an increase in the information component (IC) for simvastatin and rhabdomyolysis following initial exposure and throughout the surveillance window. For example, the change in IC was 0.266 for the surveillance period of 1-30 days as compared to the control period of -180 to -1days. Our modification of the existing OHDSI software allowed for faster queries and more efficient generation of chronographs.Conclusion Our OMOP replication matched the results of the original THIN study, only simvastatin had a signal. The TPD method is a useful signal detection tool that provides a single statistic on temporal association and a graphical depiction of the temporal pattern of the drug outcome combination. It remains unclear if the method works well for rare ADRs, but it has been shown to be a useful risk identification tool for longitudinal observational databases. Future work should compare the performance of TPD with other pharmacoepidemiology methods and mining techniques of signal detection. In addition, it would be worth investigating the relative TPD performance characteristics using a variety of observational data sources.

A Temporal Pattern Discovery Method and its Application to Physiological Data: A Case Study (Preprint)

BACKGROUND High frequency data collected from monitors and sensors that provide measures relating to patients’ vital status in intensive care units (NICUs) has the potential to provide valuable insights which can be crucial when making critical decisions for the care of premature and ill term infants. However, this exercise is not trivial when faced with huge volumes of data that are captured every second at the bedside/home. The ability to collect, analyze and understand any hidden relationships in the data that may be vital for clinical decision making is a central challenge. OBJECTIVE The main goal of this research is to develop a method to detect and represent relationships that may exist in temporal abstractions (TA) and temporal patterns (TP) derived from time oriented data. The premise of this research is that in clinical care, the discovery of unknown relationships among physiological time oriented data can lead to detection of onset of conditions, aid in classifying abnormal or normal behaviors or derive patterns of an altered trajectory towards a problematic future state for a patient. That is, there is great potential to use this approach to uncover previously unknown pathophysiologies that are present in high speed physiological data. METHODS This research introduces a TPR process and an associated TPRMine algorithm which adopts a stepwise approach to temporal pattern discovery by first applying a scaled mathematical formulation of the time series data. This is achieved by modelling the problem space as a finite state machine representation where for a given timeframe, a time series data segment transitions from one state to another based on probabilistic weights and then quantifying the many paths a time series data may transition to. RESULTS The TPRMine Algorithm has been designed, implemented and applied to patient physiological data streams captured from the McMaster Children’s Hospital NICU. The algorithm has been applied to understand the number of states a patient in a NICU bed can transition to in a given time period and a demonstration of formulation of hypothesis tests. In addition, a quantification of these states is completed leading to creation of a vital scoring. With this, it’s possible to understand the percent of time a patient remains in a high or low vital score. CONCLUSIONS The developed method allows understanding the number of states a patient may transition to in any given time period. Adding some clinical context to the identified states facilitates state quantification allowing formulation of thresholds which leads to generating patient scores. This is an approach that can be utilized for identifying patient at risk of some clinical condition prior to disease progress. Additionally the developed method facilitates identification of frequent patterns that could be associated with generated thresholds.

Heuristic Search Based Feature Selection and Discretive Self-Organized Map Clustering for Spatio-Temporal Pattern Discovery

Spatio-temporal pattern discovery is an essential one in data mining for predictive analytics. Since it manages both space and time information depending on their characteristics and the preferred applications performances. The predictive analytics uses the Spatio-temporal features to discover future outcomes. The several works have been done in the Spatio-temporal pattern discovery. But the accurate pattern discovery is the major challenges. In order to improve the accurate pattern discovery, Heuristic Best-First Search based Discretized Self-Organizing Feature Map (HBFS-DSOFM) Model is introduced. The HBFS-DSOFM model comprises two processes namely, Spatio-temporal feature selection and clustering. Initially, the Heuristic Best-First Search Algorithm is used for selecting the relevant Spatio-temporal features from the large dataset for pattern discovery. Best-first search explores a decision tree for selecting the relevant Spatio-temporal features through the maximum information gain value. After that, the Spatio-temporal data are clustered with the selected features by using Discretized Self-Organizing Feature Mapping Algorithm for Spatio-temporal pattern discovery. In Discretized Self-Organizing Feature Mapping, input spatio-temporal data is connected to the prototype neurons through the synaptic weight. For the clustering process, weights of the neurons (i.e. cluster) are initialized with random values. After that, the Manhattan distance is used to compute the distance between the input vector and cluster weight value. The gradient descent is applied to discover closest distance. The cluster whose weight is closest to the input data is grouped into the particular cluster. Then the weight of the cluster is updated with the previous weight value for grouping the entire data. This clustering process gets iterated until it satisfies termination condition. Finally, the outputs of Spatio-temporal data are combined to form a spatio-temporal pattern for efficient predictive analytics. Experimental evaluation is carried out for El Nino Dataset and taxi trajectory dataset using the factors such as time complexity, clustering accuracy, and false positive rate. The results confirm that the proposed HBFS-DSOFM model increases the Spatio-temporal pattern discovery in terms of high clustering accuracy with a less false positive rate as well as minimum time complexity. Based on the clarification, HBFS-DSOFM model is more efficient than the state-of-the-art methods.