Business Intelligence Development by Analysing Customer Sentiment
01 Aug 2018-pp 287-290
TL;DR: In real life it is often found that a particular attribute is present in VDWs that is missing in actual data warehouse, so the system needs to decide whether the attribute will be added in to physical data warehouse or not.
Abstract: Virtual Data warehouses (VDW) are generally used to store and analyze rapidly generated data and thereafter to make quick decision. VDW may stores data in a schema-less form and without any pre-processing to make the decision making on the fly. But for long term and effective business report generation, VDWs must be linked with physical data warehouse. In real life it is often found that a particular attribute is present in VDWs that is missing in actual data warehouse. In this type of situation the system needs to decide whether the attribute will be added in to physical data warehouse or not. Also in many time it is found that a particular attribute has a poor priority for data analysis, but it found very importance in VDWs. To handle all these, alone VDWs or client ends are not fit enough as they don’t have all the information about the system. Hence a specially designated node is required for gathering all the information about the system and changing the structure of the data warehouse.
Citations
More filters
01 Jun 2021
TL;DR: In this article, the role of business intelligence as a solution to illustrate its potential in risk management particularly for decision-makers in agricultural insurance was investigated, and the results identified financial risks that lead to a framework of controlling risk based on business intelligence in the agricultural insurance fund.
Abstract: The increasing data scales in today’s business sectors coupled with the necessity of risk management raise the importance of business intelligence tools as an integrated solution for the insurance industry. These tools have mostly been used to achieve effective risk management. Although methods of risk management in the insurance industry have been proposed many years ago, the research effort has primarily been focused on predictive analyses. This study aimed to investigate the role of business intelligence as a solution to illustrate its potential in risk management particularly for decision-makers in agricultural insurance. We hypothesized that this would make a preferable decision in uncertain conditions. Sample data from the online transaction process system of Iran agricultural insurance fund were preprocessed in SQL server. Multidimensional online analytical processing architecture was analyzed using Targit business intelligence tool. Our results identified financial risks that lead to a framework of controlling risk based on business intelligence in the agricultural insurance fund.
2 citations
01 Jan 2020
TL;DR: The aim of this paper is to introduce selected statistical methods that were used and implemented in real information system development (IS) for a subsidiary of a multinational corporation to produce of components for train brakes.
Abstract: The aim of this paper is to introduce selected statistical methods that were used and implemented in real information system development (IS). The entire information system has been developed for a subsidiary of a multinational corporation to produce of components for train brakes. The purpose of this statistical analysis is to obtain as much information as possible about the data collected by the collection system in order to support managerial decision-making processes as well as to set economic goals and budgets for the following period based on information on spare parts and production failures facilities. Subsequently, the system can optimize the inventory and thus save significant financial resources.
1 citations
01 Jan 2022
TL;DR: In this article, a modified Prophet forecasting model is proposed for online retailing, which emphasizes more upon customers' feedback to increase the effect of bullwhip effect on future business growth.
Abstract: Bullwhip effect is a distribution channel phenomenon caused by the unmeasured inflated ordering details that move upstream at every level of supply chain. If Bullwhip effect oppressed supply chain management a lot, then it results business loss. Nowadays, due to incorporating new business plans in online retailing, uncertain and fluctuating business growths are noticed very frequently. Fluctuating business growth should address quickly, otherwise there is a chances for generating erroneous ordering that in turn could increase the effect of bullwhip. Another reason for increasing bullwhip effect is poor forecasting of sale. Future business progress depends not only upon present sale but also upon customers’ feedback about that product. Specially, in case of online retailing, customers’ feedback is one of the important factors for future business growth. In this research, we have proposed a modified Prophet forecasting model for emphasizing more upon customers’ feedback. Fluctuating business growths are handled through the concept of virtual data warehouse. Experimental result shows the efficiency of proposed model.
References
More filters
14 May 2013
TL;DR: This paper will show where GLOBALFOUNDRIES is and where it is heading to manage the increasing needs for handling larger amounts of data with faster as well as secure access for more users.
Abstract: As a new company, GLOBALFOUNDRIES is aggressively agile and looking at ways to not just mimic existing semiconductor manufacturing data management but to leverage new technologies and advances in data management without sacrificing performance or scalability. Being a global technology company that relies on the understanding of data, it is important to centralize the visibility and control of this information, bringing it to the engineers and customers as they need it. Currently, the factories are employing the best practices and data architectures combined with business intelligence analysis and reporting tools. However, the expected growth in data over the next several years and the need to deliver more complex data integration for analysis will easily stress the traditional tools beyond the limits of the traditional data infrastructure. The manufacturing systems vendors need to offer new solutions based on Big Data concepts to reach the new level of information processing that work well with other vendor offerings. In this paper, we will show where we are and where we are heading to manage the increasing needs for handling larger amounts of data with faster as well as secure access for more users.
32 citations
"Business Intelligence Development b..." refers background in this paper
...Several researches [6][2] show that ETL consumes a lot of time, resources and effort of total DW project which in turn delays data availability....
[...]
TL;DR: A new approach to identify emerging customer needs in the growing popular online interactive environment with customer participation is reported, using the Bayes factor to calculate the likelihood that current offering cannot meet the customer's requirements whenever a new specification is incorporated.
Abstract: Rapid changes of new technologies, market dynamics, and swift fluctuation of customer tastes acerbate the needs for companies to identifying the emerging customer requirements and incorporate them in the conceptual design stage. Discovering emerging customer needs has great potential to create new product opportunities for the success of business. However, identifying customers' requirements in an early design stage has not been well addressed in the traditional design methodology. Because emerging needs are usually not obvious at the budding stage, the related observations are rare in dataset. Traditional methods fall short of providing enough support of eliciting the below-the-radar needs. This paper reports a new approach to identify emerging customer needs in the growing popular online interactive environment with customer participation. The Bayes factor, a methodology to quantify the occurrence possibility of a certain event, is used to calculate the likelihood that current offering cannot meet the customer's requirements whenever a new specification is incorporated. With the sequential input from customers, a series of the Bayes factor value can then be calculated as the weight of evidence that emerging customer needs appear. We show that the decreased value will be the potentially emerging needs which cannot be satisfied by the current product family. Numerical and analytical results are derived to demonstrate the viability and effectiveness of the proposed approach.
27 citations
"Business Intelligence Development b..." refers background or methods in this paper
...A tool based analysis named as performance dashboard and a Key Performance Indicators (KPIs)[13] for measuring and monitoring changes of the business was proposed for better monitoring of busines....
[...]
...But, it is found in research [13][14][16] that the needs of customer changes over the time....
[...]
...In [13] they focused on customer’s participation by an online interactive environment with the use of Bayes factor....
[...]
...These all are basically designed for customer requirement analysis [10] [13] [14] [16] and to track required business changes....
[...]
TL;DR: This research work dynamically finds the most cost effective path from the lattice structure of cuboids based on concept hierarchy to minimize the query access time.
Abstract: Analytical processing on multi-dimensional data is performed over data warehouse. This, in general, is presented in the form of cuboids. The central theme of the data warehouse is represented in the form of fact table. A fact table is built from the related dimension tables. The cuboid that corresponds to the fact table is called base cuboid. All possible combination of the cuboids could be generated from base cuboid using successive roll-up operations and this corresponds to a lattice structure. Some of the dimensions may have a concept hierarchy in terms of multiple granularities of data. This means a dimension is represented in more than one abstract form. Typically, neither all the cuboids nor all the concept hierarchy are required for a specific business processing. These cuboids are resided in different layers of memory hierarchy like cache memory, primary memory, secondary memory, etc. This research work dynamically finds the most cost effective path from the lattice structure of cuboids based on concept hierarchy to minimize the query access time. The knowledge of location of cuboids at different memory elements is used for the purpose.
13 citations
14 Jul 2008
TL;DR: A virtual data warehouse to use GIS information is proposed to manage and collect data acquired by and from several sources and allows users to access to environmental data collected by different sources, to register, normalize and visualize data, to process data using distributed computing resources and web applications.
Abstract: Environmental monitoring requires that raw data acquired from sensors and/or data repositories be transformed, by scientific analysis, into assessments of current ecosystem conditions and in evolution trends in time and space. The huge data amount produced by different sources, the complexity of the environmental models adopted and the necessary distributed collaboration between scientists and government agencies, require specific applications to process and understand environmental phenomena and validate results. GIS domain received a great deal of attention from the scientific and industrial applications communities. Many algorithms, protocols, and applications have been built through the ears for the collection, investigation, analysis, and synthesis of data obtained from sensors ranging from temperature, pressure, etc. to satellite imaging. Almost all attempts have been made to deal with data obtained from lumped repositories. Little or almost none works are reported about a general and flexible mechanism used to display geo-dependent data as it is generated. In this paper we present a GIS platform whose goal is to efficiently mine, fuse, and exploit environmental data and to synthetically display the results at the pace the data is produces. A virtual data warehouse to use GIS information is proposed to manage and collect data acquired by and from several sources. The proposed platform allows users to access to environmental data collected by different sources, to register, normalize and visualize data for exploring and analyzing complex structure and relationship, to process data using distributed computing resources and web applications. To evaluate the effectiveness of the proposed prototype, we present a case study related to data fusion of Modis files and Geo-Located real sensor data for air quality monitoring.
10 citations
"Business Intelligence Development b..." refers background in this paper
...Data virtualization are generally performed at implementing site consisting of typically one to three months data [7][8][12]....
[...]
...That is maintaining Virtual Data Warehouse (VDW) [4][7][8] for such rapidly generated data, where the data are stored in a unstructured form and not required to be modeled or transformed through ETL....
[...]
01 Aug 2017
TL;DR: The objective of this paper is to analyze the credit risk and loan performance of the “Lending Club” company which is one of the biggest market place for online credit.
Abstract: As of now, currently there is a tremendous rise in the economy development due to which there has been a huge rise in the requirement of the personal loan of customers as the behavior of the borrowers have uncertainty and fuzzy nature. For both lenders and borrowers, credit risk is a major challenge, which directly or indirectly affects the reliability of the banks. Present article has concentrated on menace by granting loans to the customers, risk related to the investors. The objective of this paper is to analyze the credit risk and loan performance of the “Lending Club” company which is one of the biggest market place for online credit. Analyses of the performance of the bank loan and credit risk on the large dataset having 112 attributes which have been collected from the Lending Club of the period 2012 and 2016. In this paper, Hadoop approach has been used and for applying Hadoop methodology we will be using the Cloudera software which is an open source platform for analyzing the data. It supports the Hadoop ecosystem which is used for the managing, storing and analyzing the large volume of data. In this article, we used the Hive which is data warehouse system and which is used for managing and analyzing the data stored in HDFS (Hadoop Distributed File System) using HiveQL. To understand the performance of the bank loan data we had performed various analyses on the collected dataset of the bank.
10 citations
"Business Intelligence Development b..." refers background in this paper
...To solve this problem the concept of data virtualization and virtual data warehouse [4] [5][11] is being introduced....
[...]