Businesses have huge amounts of data (master data) collected over time. These data are historical data. The data would be used for understanding business dynamics that have happened in the past years for future benefits. This paper will focus on data mining, data analysis and data profiling in marketing, in a mobile telecommunications industry. A company in mobile telecommunications industry has master data collected from its customers. These data are stored in a central warehouse in the company. When such data are mined, analysed and profiled, they can provide business insights, which could lead, to increase in sales of products and services.
Data mining in the marketing department, in a mobile telecommunications industry
Data mining involves the analysis of huge amounts of raw data collected over time and stored in data warehouses. It is a subset of data analysis that is based on modelling techniques (Loshin, 2008). Data mining in the marketing department of the mobile telecommunications industry would encompass sifting master data by use of algorithms. Marketing is a core business in such an industry. The management would carry out data mining to understand customer behavior over time.
For instance, months during the year during which customers buy most or least products and services. It would also reveal the customers who are the biggest spenders for certain products and services. When the company management thinks of carrying out a promotion it will look at the data mined from the static warehouse for information that will help strategize on the promotion (Loshin, 2008). The company’s market segment would be reflected on the results of the mined data. In essence, the marketing department of the company would use the results of the mined data to predict the future; using past data.
Data analysis in the marketing department, in a mobile telecommunications industry
Data analysis is statistics based process of manipulating data in order to come up with useful conclusions inferred from the information analyzed. It is divided into three main stages; data cleaning, initial data analysis and main data analysis. Data cleaning involves sorting out data. During the initial data analysis, quality measurements, primary transformations and characteristic of data are analyzed. In the main data analysis step, confirmatory and statistical approaches are applied. ANOVA, MANOVA, correlation analysis, t-tests and regression analysis are some of the analyses used for this descriptive statistical approach.
The marketing department of the telecommunications industry would analyse its master data to make some inference based on the data they have analysed. They would follow the simple statistical rubric of making generalized conclusions from sample data. The core marketing department can use the data analysis results for predicting the turnover of various products and services among different departments within the firm. The analyses could also be utilized for understanding any business inefficiencies and come up with strategies to re-engineer the processes (Otto, Hüner & Österle, 2012).
Data profiling in the marketing department, in a mobile telecommunications industry
Data profiling is a technical method of understanding technical issues of master data. It involves the use of various statistical approaches for profiling the data. The marketing department of the telecommunications industry would use data profiling to discover some important technical aspects of the master data in the warehouse. These aspects may include missing data, illegal entries, duplicated values and misspelling. The department would perform the data profiling procedure throughout the year to ensure that the data stored in the warehouse are the right data, free from technical errors (Otto et al., 2012).
Challenges to data mining, data analysis and data profiling
There are challenges for successful data mining, data analysis and data profiling by organizations (Silvola, Jaaskelainen, Kropsu-Vehkaper & Haapasalo, 2011). One of these challenges is lack of human resource that can think about adding value by working on the master data collected by the organization over time. In this case, the human resource does not recognise, or rather understand the potential of the master data in the warehouse.
This may be due to lack of the right employees who have the technical knowledge of conducting data mining, data analysis and data profiling (Silvola et al., 2011). Another challenge in implementing these approaches is wrong statistical applications in data mining, data analysis and data profiling. It implies that wrong data will be used, for instance, in data analysis before data cleaning. This would culminate in inaccurate sample data results and thus, wrong inferences are made concerning the whole market population under study
Strategies to minimize challenges in data mining, data analysis and data profiling
An organization ought to put in place strategies that hamper data mining, data analysis and data profiling. It should have human resource trained on the benefits of using master data of the organization. The training should emphasize on the benefits that the organization would derive from such utilization. The human resource should also be trained on the right statistical tools and approaches for data mining, data analysis and data profiling. Through this, the organization would benefit strongly from its master data (Silvola et al., 2011).
References
Loshin, D. (2008). Master data management. Burlington, MA: Morgan Kaufmann.
Otto, B., Hüner, K. M., & Österle, H. (2012). Toward a functional reference model for master data quality management. Information Systems and e-Business Management, 10(3), 395-425.
Silvola, R., Jaaskelainen, O., Kropsu-Vehkapera, H., & Haapasalo, H. (2011). Managing one master data–challenges and preconditions. Industrial Management & Data Systems, 111(1), 146-162.