In this paper a system for voice of customer analysis is proposed, which will produce strong rules to help organization to take business decisions. It uses parallel association rule mining for rule generation and data usually tends to be very huge so partitioning is done on the basis of sentiment of customer. For this purpose text mining algorithm is used which extracts information from unstructured data. On these partitions of data association rule mining algorithm is applied which determines strong association rules and kept in a database. Domain experts can use these rules to take business decisions which can help an organization to have a better understanding of customer's all needs and wants.Keywords voice of customer analysis, text mining, parallel association rule mining, sentiment analysis. I. INRODUCTIONoice of customer analysis is all about in-depth market research which produces customer needs and wants. Market basket analysis is a good way to provide scientific decision support for retail market by mining association relationships among items people purchased together. Mining results may not be interesting to people since they don't show semantic associations among items. However, the consequence may be different if association rules are mined on items' internal characteristics.All the needs and wants of customers are needed to be considered for the start of new product.. Voice of customer will help understanding the customer's requirement. Now a days product should not only have "nothing wrong" but should also maximize positive quality such as ease of use and convenience, which adds value to product and leads for customer satisfaction. So voice of customer can be used for quality function deployment (QFD) and detailed design specification Voice Of Customer:Voice of Customer (VoC) refers to customer communications such as conversational voice, Recordings, Emails, text messages, chat transcripts, agent notes. Most of the VoC is collected through contact centres. Apart from deriving valuable insights through contact centres it is possible to influence the customer back through contact centres based on those insights. However, carrying this out in an effective manner requires effective BI systems for VoC.Voice of customer may contain Phrases that provide valuable feedback to the enterprise, Phrases that refer to service quality issues and point to efficiency lapses. VoC also reflect the sentiments and opinions of the customers and indicate the level of (dis)satisfaction of the customer or his churn propensity. VoC also point to the products, services and features customers are interested in.Enterprises have access to such kind of valuable information only through the VoC. However VoC is often noisy with multilingual phrases, unconventional abbreviations and short hands, spelling and grammatical mistakes. There are three major issues in using VoC for BI.
For estimating software, system size is the main parameter of the system development effort. It affects substantially on accurate estimation of effort of development. The Predictive Object Point (POPs) input gives an estimate of the size of the software for which the estimation is required. POPs are a metric suitable for estimating the size of object oriented software, based on the behaviors that each class is delivering to the system along with top level inputs describing the structure of a system. However there is no real mapping of Source Lines of Code (SLOC) to POPs exists. This paper is an attempt to map the Predictive Object Point Metrics with software size which may help in further prediction of effort. This may also help in estimation of cost as well as schedule measurement of an OO system. The proposed method of mapping between POP and software size has been empirically investigated. KLOC has been estimated in terms of EKLOC through POP count using the linear regression equation. The results are presented here to show that how POP Count may be mapped to corresponding software size (KLOC) of an object oriented system.
The visible appearance of the emotion state, personality, purpose, psychological feature activity and psychopathology of an individual is the Facial expression. This plays an outgoing role in social affairs. Automatic recognition of facial expressions will be a vital part of natural human-machine interfaces. It should even be applied in activity science and in clinical apply. Fellows in nurturing automatic facial features Recognition system must perform detection and placement of faces during a disordered scene, facial feature extraction and facial features classification. Emotion recognition by facial features utilizes a Deep Learning system, which is enforced victimization Convolution Neural Network (CNN). The CNN model of the project relies on LeNet design. Kaggle facial features dataset with seven facial features labels as fear, anger, happy, surprise, sad, neutral and disgust is employed during this project. The system achieved 60.37 accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.