17-07-2012, 11:37 AM
Can u send me the ppt for A Framework for Personal Mobile Commerce Pattern Mining and Prediction
17-07-2012, 11:37 AM
Can u send me the ppt for A Framework for Personal Mobile Commerce Pattern Mining and Prediction
07-11-2012, 12:13 PM
A Framework for Personal Mobile Commerce Pattern Mining and Prediction
A Framework for Personal.pdf (Size: 432.1 KB / Downloads: 134) Abstract Due to a wide range of potential applications, research on mobile commerce has received a lot of interests from both of the industry and academia. Among them, one of the active topic areas is the mining and prediction of users’ mobile commerce behaviors such as their movements and purchase transactions. In this paper, we propose a novel framework, called Mobile Commerce Explorer (MCE), for mining and prediction of mobile users’ movements and purchase transactions under the context of mobile commerce. The MCE framework consists of three major components: 1) Similarity Inference Model (SIM) for measuring the similarities among stores and items, which are two basic mobile commerce entities considered in this paper; 2) Personal Mobile Commerce Pattern Mine (PMCP-Mine) algorithm for efficient discovery of mobile users’ Personal Mobile Commerce Patterns (PMCPs); and 3) Mobile Commerce Behavior Predictor (MCBP) for prediction of possible mobile user behaviors. To our best knowledge, this is the first work that facilitates mining and prediction of mobile users’ commerce behaviors in order to recommend stores and items previously unknown to a user. We perform an extensive experimental evaluation by simulation and show that our proposals produce excellent results. INTRODUCTION ITH the rapid advance of wireless communication technology and the increasing popularity of powerful portable devices, mobile users not only can access worldwide information from anywhere at any time [28] but also use their mobile devices to make business transactions easily, e.g., via digital wallet. Meanwhile, the availability of location-acquisition technology, e.g., Global Positioning System (GPS), facilitates easy acquisition of a moving trajectory, which records a user movement history. Thus, we envisage that, in the coming future of Mobile Commerce (M-Commerce) age [27], some m-commerce services will be able to capture the moving trajectories and purchase transactions of users. Take the recent announced Shopkick [20] as an example, it gives mobile users rewards and offers when users checkin in stores and on items. Anticipating that some users may be willing to exchange their locations and transactions for good rewards and discounts, we expect more mobile commerce applications, whether they will bear a business model similar with Shopkick or not, will appear in the future. RELATED WORK In this section, we review and classify relevant previous studies into three categories: 1) similarity measures, 2) mobile pattern mining techniques, and 3) mobile behavior predictions. Similarity Measure. There have been many studies on measuring the similarity between two objects. The first one is based on multiple-level hierarchical structures. In [15], Lu first proposes the concept of multiple-level hierarchical structure in data mining. In [6], Han et al. propose the multiple-level association rules mining. In this study, taxonomy is incorporated for representing the hierarchical relations of items. In [26], Tseng et al. first applies the multiple-level hierarchical concept to mine associated service patterns in mobile web environments. Based on the structure, the items in the same level are regarded as similar items. However, we do not know the relations between the items in the different levels. The second one is sequence alignments. In [11], Jeh et al. propose the SimRank to iteratively compute the similarities between objects. The idea is that two objects are similar if they are related to similar objects. To improve the efficiency of SimRank, in [32], Yin et al. develop the hierarchical structure named SimTree to reduce the computation cost and the storage of object similarities but still discover the relationships between objects. In [29], Xin et al. propose a pattern distance measure based on set similarity between two association patterns. The concept of set similarity is to apply Jaccard Measure to calculate the similarity of two sets. Let S1 and S2 be two sets, the set similarity set_similarity(S1, S2) is defined as (1). However, set similarity is not applicable to store similarity in mobile commerce. System Framework The proposed MCE framework consists of three modules, 1) a mobile network database, 2) a data mining mechanism, and 3) a behavior prediction engine (See Fig. 2). The mobile network database maintains detailed store information which includes locations. Our system has an “offline” mechanism for similarity inference and PMCPs mining, and an “online” engine for mobile commerce behavior prediction. When mobile users move between the stores, the mobile information which includes user identification, stores, and item purchased are stored in the mobile transaction database. Table 2 shows an example of mobile transaction database which contains 4 users and 14 mobile transaction sequences. In the offline data mining mechanism, we develop the SIM model and the PMCP-Mine algorithm to discover the store/item similarities and the PMCPs, respectively. In the online prediction engine, we propose a mobile commerce behavior predictor (MCBP) based on the store and item similarities as well as the mined PMCPs. When a mobile user moves and purchases items among the stores, the next steps will be predicted according to the mobile user’s identification and recent mobile transactions. The framework is to support the prediction of next movement and transaction. Similarity Inference Model (SIM) An essential task in our framework is to determine the similarities of stores and items. The problem may be solved by using store and item category ontology. However, the store or item ontology may not match with the mobile transaction database. Our goal is to automatically compute the store and item similarities from the mobile transaction database, which captures mobile users’ moving and transactional behaviors (in terms of movement among stores and purchased items). EXPERIMENTAL EVALUATION We conduct a series of experiments to evaluate the performance of the proposed framework MCE and its three components, i.e., SIM, PMCP-Mine, and MCBP under various system conditions. The synthetic data generator is described in Section 5.1. In the experiments, we evaluate the precision of mobile behavior prediction under a number of examined prediction methods. All of the experiments were implemented in Java on a 3.0 GHz machine with 1 GB of memory running windows XP. Simulation Model The simulation model has been adopted by Yun et al. [30] as well. Table 8 summarizes the major parameters in the simulation model and their default values. In the base experiment model, we use a |W|
26-11-2012, 12:01 PM
to get information about the topic "Framework for Personal Mobile Commerce Pattern Mining and Prediction " full report ppt and related topic refer the link bellow
https://seminarproject.net/Thread-a-fram...prediction https://seminarproject.net/Thread-a-fram...n-abstract
02-03-2013, 08:49 PM
can u plz send me the ppt for framework for personal mobile pattern mining and prediction.
04-03-2013, 10:52 AM
to get information about the topic "a framework for personal mobile commerce pattern mining and prediction" full report ppt and related topic refer the link bellow https://seminarproject.net/Thread-a-fram...prediction https://seminarproject.net/Thread-a-fram...n-abstract |
|