CAPReS: Context Aware Persona Based Recommendation for Shoppers
Authors: Joydeep Banerjee, Gurulingesh Raravi, Manoj Gupta, Sindhu Ernala, Shruti Kunde, Koustuv Dasgupta
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In our empirical evaluations with a mix of realworld data and simulated data, the performance of the heuristic in terms of the persona based recommendations (quantified by similarity scores and items recommended) closely matched (differed by only 8% each with) that of the dynamic program and at the same time heuristic ran at least twice faster compared to the dynamic program. |
| Researcher Affiliation | Collaboration | Joydeep Banerjee Arizona State University jbanerje@asu.edu Gurulingesh Raravi Xerox Research Center India gurulinges.raravi@xerox.com Manoj Gupta Xerox Research Center India manoj.gupta@xerox.com Sindhu K. Ernala IIIT Hyderabad eskiranmai94@gmail.com Shruti Kunde and Koustuv Dasgupta Xerox Research Center India {firstname.lastname}@xerox.com |
| Pseudocode | Yes | Algorithm 1: Substructure to obtain the list OP t ,v,i,b of top-k recommendations in the dynamic table |
| Open Source Code | No | The paper does not include an unambiguous statement that the authors are releasing the code for the work described in this paper, nor does it provide a direct link to a source-code repository. |
| Open Datasets | No | The paper describes how the data was generated using real-world sources and APIs, but does not provide concrete access information (link, DOI, formal citation for a downloadable dataset) for a publicly available or open dataset. |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training or validation. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions the use of 'Google Directions, Places and Geocode APIs' and refers to specific algorithms like 'Eppstein’s Algorithm' and 'MCKP (Pisinger 1995)' but does not provide specific version numbers for any software, libraries, or solvers used in the experiments. |
| Experiment Setup | Yes | The experiments were performed using a mix of real-world data and randomly generated data. The road network was generated using the real-world data, i.e., stores, their locations, inventory and their costs, landmarks and commute time between each of these nodes were generated from real-world data whereas user queries (products to purchase, source and destination, cost and time constraints) were generated randomly. Specifically, the data was generated as follows. The road network (i.e. landmarks, stores, and commute times) was generated using Google Directions, Places and Geocode APIs for a locality called Whitefield in Bengaluru city in India. 20 user queries were randomly generated in which 4 queries were for purchasing 2 products and 16 queries were for purchasing 3 products. The cost and budget constraints were set to INR 2500 (Indian Rupee) and 35 mins respectively. The source and destination of the shopper for each query were chosen such that there is at least one path that satisfies the time constraint. Out of the 20 generated problem instances, 10 were for luxuriant and 10 were for infrequent shoppers. Accordingly, for each instance, similarity scores were computed as discussed in Section 4; similarity score for a given product is a real number in the range 0 to 1. |