Factorizing Historical User Actions for Next-Day Purchase Prediction

It is common practice for many large e-commerce operators to analyze daily logged transaction data to predict customer purchase behavior, which may potentially lead to more effective recommendations and increased sales. Traditional recommendation techniques based on collaborative filtering, although having gained success in video and music recommendation, are not sufficient to fully leverage the diverse information contained in the implicit user behavior on e-commerce platforms. In this article, we analyze user action records in the Alibaba Mobile Recommendation dataset from the Alibaba Tianchi Data Lab, as well as the Retailrocket recommender system dataset from the Retail Rocket website. To estimate the probability that a user will purchase a certain item tomorrow, we propose a new model called Time-decayed Multifaceted Factorizing Personalized Markov Chains (Time-decayed Multifaceted-FPMC), taking into account multiple types of user historical actions not only limited to past purchases but also including various behaviors such as clicks, collects and add-to-carts. Our model also considers the time-decay effect of the influence of past actions. To learn the parameters in the proposed model, we further propose a unified framework named Bayesian Sparse Factorization Machines. It generalizes the theory of traditional Factorization Machines to a more flexible learning structure and trains the Time-decayed Multifaceted-FPMC with the Markov Chain Monte Carlo method. Extensive evaluations based on multiple real-world datasets demonstrate that our proposed approaches significantly outperform various existing purchase recommendation algorithms.

Analysis of Information Technology (IT) Goods Sales Patterns Using the FP-Growth Algorithm

Determination of sales patterns is very important in marketing. Sales pattern serves to conduct an effective analysis in improving marketing. Sales analysis aims to explore new knowledge that can help design effective strategies by utilizing sales transaction data. This study processes sales data for 12 transaction days containing 47 items using the Fp-Growth algorithm. The results of this study are items with a minimum value of support > 0.10 and confidence 0.60 and will be compared with testing data using RapidMiner to test whether the results are valid so that the test results can help in designing sales strategies.

Parallel analysis of Ethereum blockchain transaction data using cluster computing

Ability to perform fast analysis on massive public blockchain transaction data is needed in various applications such as tracing fraudulent financial transactions. The blockchain data is continuously growing and is organized as a sequence of blocks containing transactions. This organization, however, cannot be used for parallel graph algorithms which need efficient distributed graph data structures. Using message passing libraries (MPI), we develop a scalable cluster-based system that constructs a distributed transaction graph in parallel and implement various transaction analysis algorithms. We report performance results from our system operating on roughly 5 years of 10.2 million block Ethereum Mainnet blockchain data. We report timings obtained from tests involving distributed transaction graph construction, partitioning, page ranking of addresses, degree distribution, token transaction counting, connected components finding and our new parallel blacklisted address trace forest computation algorithm on a 16 node economical cluster set up on the Amazon cloud. Our system is able to construct a distributed graph of 766 million transactions in 218 s and compute the forest of blacklisted address traces in 32 s.

Data interaction model for power transaction based on CIM

With the increase of power transaction business, traditional power transaction data interaction models cannot fully meet the needs of data interaction. The data model conforming to the power transaction data architecture plays an important role. Data interaction requirements of Chinese electricity market transaction business are analyzed, and the specific method of power transaction data description is given in the IEC-61970 protocol standard. Also a common information model (CIM) for electricity trans-action data interaction is built that conforms to the data interaction architecture. Finally the functional description of the model is built adopting the unified modeling language (UML). Compared with the existing electricity transaction data interaction model, the method is beneficial to reduce the degree of data redundancy, increase the speed of data interaction, and thus improve the transaction efficiency of the electricity market.

Strategic Planning Needs the Right Information

There is a need to undertake a considerable research and analysis project to search out and gather the requisite information required for business development. A prerequisite is the need to better understand what is meant by the terms data and information, as they are often used interchangeably. What kind of information is required for business development, and where and how it can be found? There is the ‘hard' transaction data from software applications that help manage operations. This data is provided by the information system and can give strategic performance information. A review of the staff competencies can indicate the potential for business advantage. It is helpful to discover the dependencies between business activities. The complexity and volume of data to be searched and analysed indicates a need for a special information management project. It is imperative to store the information appropriately with a clear architectural structure for easy retrieval.

The Impact of the COVID-19 Pandemic on Consumption: Evidence from Weekly UnionPay Card Transaction Data in Shanghai

The new coronavirus outbreak provides a genuinely exogenous unanticipated shock that enables this study to identify its impact on offline consumption, using unique weekly UnionPay card transaction data in 16 districts of 206 business circles in Shanghai, after China’s outbreak in late January 2020. Based on the difference-in-differences estimation strategy, this study finds that weekly offline consumption fell by 1.843 million RMB, and offline consumption frequency fell 447 times per business circle during the 20 subsequent weeks. It also finds a significant heterogeneity effect on different districts and categories, different times in a day of offline consumption spending in the post-COVID-19 pandemic window period, in which the government implemented different level policy responses for major public health emergencies. These findings suggest that offline consumption fell drastically after the unanticipated pandemic shock, which also means that policymakers need to be cautious in achieving a balance between economic recovery and epidemic prevention and control.

Exploring the Geographic Variation in Fruit and Vegetable Purchasing Behaviour Using Supermarket Transaction Data

The existence of dietary inequalities is well-known. Dietary behaviours are impacted by the food environment and are thus likely to follow a spatial pattern. Using 12 months of transaction records for around 50,000 ‘primary’ supermarket loyalty card holders, this study explores fruit and vegetable purchasing at the neighbourhood level across the city of Leeds, England. Determinants of small-area-level fruit and vegetable purchasing were identified using multiple linear regression. Results show that fruit and vegetable purchasing is spatially clustered. Areas purchasing fewer fruit and vegetable portions typically had younger residents, were less affluent, and spent less per month with the retailer.

Penerapan Asosiasi Algoritma Apriori Pada Data Penjualan Alat-Alat Listrik Dan Tekhnik

The incompatibility of information in reporting productsthat are sold, and data storage is very large, business people, especially in the sales business are required to find an appropriate strategy that can increase sales and marketing of products sold, one of which is by using electronic product sales data. Therefore, anapplication is needed that is able to sort and select data, so that information can be obtained that is useful for users, namely data mining. Associate patterns can be used to place products that are often purchased together into an area that is close together so as to facilitate the customer in finding the desired product and designing the appearance of products in the catalog. The method used is theApriori Algorithm method, with the help ofTanagra 1.4.50 tools and processing transaction data using Microsoft Excel 2007.

Predicting Partner’s Digital Transformation Based on Artificial Intelligence

Partner’s digital transformation is one of the most important metrics for businesses, particularly for businesses in the subscription world. Hence, how to predict partner transformation is a consistent focus in the industry. In this paper, we use an AI (Artificial Intelligence) relevant algorithm to analyze partner’s digital transformation issues and propose a novel method, named the hybrid VKR (VAE, K-means, and random forest) algorithm, to predict partner transformation. We apply our algorithm to partner transformation issues. First, we show the prediction of about 5980 partners from 25689 partners, who are transformed and sorted according to important indicators. Secondly, we recap the tremendous effort that was required by the company to obtain high-quality results for economic change when a partner is transforming along with one or many of the transformation dimensions. Finally, we identify unethical behavior by looking through deal transaction data. Overall, our work sheds light on several potential problems in partner transformation and calls for improved scientific practices in this area.