Project Objective and Scope
The role of big data analytics is very important in the business industry. By using different tools and techniques of big data analysis, we can analyse the data generated from the business industry. This data analysis is very helpful in making better decisions in the industry. We want to study the business research proposal for the business industry. For this proposal, we have to study different aspects of business and we have to propose the research study for the big data analysis. We will analyze the data generated from the telecom industry and after analysis of this data we will make conclusions. We will select the telephone operator company Vodafone, Australia. We will plan to collect the data from Vodafone and then we will analyse this data by using different statistical software’s. Let us see this research proposal in detail.
It is important to define the project objective for getting proper direction for our research work. Here, we have to arrange a research study for the analysis of big data generated in Vodafone Australia. We want to study the revenues collected from the different socio-economic classes and we will study the different trends in the expenditure for mobile data and network. We will also study some related aspects regarding the usage pattern. We will compare the usage pattern of male and female. We want to check whether there is any significant difference in the usage of mobile services by male and female.
Project Scope
Data for this research study would be collected from the secondary resources from Vodafone Australia. So, this research study would be limited for the Australia only and we cannot expand its research outcomes for entire globe. Also, this research study is based on only one telephone operator Vodafone Australia. This operator Vodafone Australia does not cover the entire population of Australia. So, results based on this study would not be exactly applicable for entire population. But according to the law of generalization, we will apply these results for entire population by using some significance level or confidence intervals. This research project has a big scope in different comparisons. For example, we will compare the shares of revenues from different socio-economic classes, different regions, gender, occupation, salary, etc.
The “Big Data” is the term which states about the data in large quantity and huge form that it cannot be managed in regular record systems, which is used to know about the organization growth. The major objective of big data is to provide large space for storing the resources, it also takes less time in calculating and used for taking business decisions at large scale (Kalyvas and Albertson, 2015).
Role of Big Data Analytics in Telecom Industry
It consists of 3v’s: velocity, variety and volume. Velocity refers to that data which is coming from the social sites like that of messages, status updates of facebook, credit card swipes, and many tweets from the twitter. Variety refers to different type of data format like unstructured, semi-structured and structured and volume refers data into the large amount. The big data has increased around 90% in world from last two years. Creation of daily big data is 2.5 bytes of quintillion. The big data is actually increasing day by day and the organizations and their analyzers don’t have knowledge and techniques to calculate huge amount of the data. Organizations do not show interest in use of big data because of lack of preparation, produces new chances and low cost in big data (Erevelles, et.al, 2016).
Big data is used in data mining and getting accurate results so that decision can be taken for further operation of the business. Every organization should take basic step to use big data into their business so they can analyze the advantages from big data which will give growth to their organization.
In a survey it was found that only 12% are using big data approach for their organizations and 71% are at initial stage of planning the big data. There are three models which have been introduced for big data first is ETL extract, second is an Interactive query and third is Predictive analytics. The major steps are as follows for the organizations who want to follow the idea of big data:
- The process of data which depends on economic, social and technical factors.
- Candidate situation, which is necessary to study so that they can decide what to be applied.
- Candidate technology, for example cloud analytics, big data visualization, and data warehouse.
- Assessment of technology indicators, like market size, strength and hurdles of any industry.
- Implication of planning technology, for big demand and optimistic (Jagadish, et.al, 2014).
For any research study, it is important to establish the hypotheses because it will provide us the proper guidelines during the working on project. For this research study scenario, we will focus on the comparison of the average expenditure on mobile by male and female customers. The primary research hypothesis and secondary research hypotheses are summarised as below:
- Primary Hypothesis
For this research study, the primary null and alternative hypotheses are defined as below:
Null hypothesis: H0: There is no any significant difference exists between the average expenditure on mobile phones by male customers and female customers.
Alternative hypothesis: Ha: There is a significant difference exists between the average expenditure on mobile phones by male customers and female customers.
- Secondary Hypothesis
For this research study, the secondary hypotheses are defined as below:
Null hypothesis: H0: There is no any significant difference exists between the average internet data usage by the male customers and female customers.
Research Hypotheses for the Study
Alternative hypothesis: Ha: There is a significant difference exists between the average internet data usage by the male customers and female customers.
A research study would be based on the data analysis from secondary sources of data. For any research study, it is important to collect the data by using proper methods of data collection. For this research study, we will use secondary data from Vodafone Australia. If the data size is very big, then we will use statistical software’s for the analysis of this data. We will only focus on the variables that are included in this research study. There would be so many variables included in the given data set, but we will only consider some variables such as monthly expenditure, gender of customer, etc. For this research study, we will analyse both type of data i.e. qualitative and quantitative data.
In this qualitative research study, we will study different types of distributions of the attributes under study. In this qualitative research study, we will find out the frequency distributions for the different categorical variables. Also, we will use bar diagrams for the comparison purpose. For this qualitative research we will use some non parametric tests of hypotheses. We will study the pattern of gender distribution over different regions. We will check the claim or hypothesis whether the distribution of the gender of customers is same in different regions or not. We will also check whether the mobile internet data usage is independent from the different regions in the Australia or not. For checking this hypothesis we will use Chi square test for independence of two categorical variables.
Quantitative research study is very important for checking different types of research hypotheses or claims. Here, first of all we will use the descriptive statistics for getting idea about the nature of data. Descriptive statistics provides us the nature and different characteristics of the variables included in the data. Also, we will use some inferential statistics for this research study. We will use different statistical tests of hypothesis for checking different claims. We will use the two sample t test for the population means for checking whether there is any significant difference exists between the average expenditure for mobile phones by the male customers and female customers. Also, we will use the one way analysis of variance or ANOVA F test for checking the hypothesis whether there are any significant differences in the average usage for different locations in the Australia. For this research study we will use appropriate tests of hypothesis and we will also check the assumptions for using these tests.
Data Collection and Analysis Methodology
This research study will be limited to single country and single mobile operator Vodafone Australia. So, we could not generalize the results of this research study for entire globe. Also, this research study could not cover the entire population of the Australia, so results would not have total reliability and flexibility for using these results. We will use some significance level and results would be significant at some level. Also, there would be chance of getting errors due to use of big data for this research study.
It is important to create a proper research plan so that we complete our research study during specified time period. For this research study, the research schedule or plan is summarised as below:
No. |
Task |
Duration |
1 |
Selection of Business Organization |
2 Days |
2 |
Deciding Research Hypothesis or claims |
2 Days |
3 |
Literature Review and study of company background |
4 Days |
4 |
Data collection from primary as well as secondary sources |
2 Days |
5 |
Data Analysis using different statistical software |
2 Days |
6 |
Analysis and drawing Conclusions |
2 Days |
7 |
Discussion on Results and conclusions |
2 Days |
8 |
Checking Validity and reliability of results by peer review |
4 Days |
This research study will be completed in 20 days, but we will keep some reliability for extension of project duration due to some critical situations or unavailability of resources. We will extend this project duration up to 30 days for getting more reliable and unbiased results.
Conclusion
This research study will allow us for the comparison between the average expenditure on mobile phone by male and female customers for Vodafone telephone operator in Australia. Research study would be based on the secondary data resources and we will us this data for checking our research hypotheses. By using this data, we will check the hypothesis whether there is a significant difference exists between the average expenditure on mobile phones by male customers and female customers. Also, we will check one more hypothesis whether there is a significant difference exists between the average internet data usage by the male customers and female customers.
Reference List
Casella, G. and Berger, R. L. (2002). Statistical Inference. Duxbury Press.
Cox, D. R. and Hinkley, D. V. (2000). Theoretical Statistics. Chapman and Hall Ltd.
Degroot, M. and Schervish, M. (2002). Probability and Statistics. Addison – Wesley.
Dobson, A. J. (2001). An introduction to generalized linear models. Chapman and Hall Ltd.
Erevelles, S., Fukawa, N. and Swayne, L., 2016. Big Data consumer analytics and the transformation of marketing. Journal of Business Research, 69(2), pp.897-904.
Evans, M. (2004). Probability and Statistics: The Science of Uncertainty. Freeman and Company.
Hastle, T., Tibshirani, R. and Friedman, J. H. (2001). The elements of statistical learning: data mining, inference, and prediction: with 200 full-color illustrations. Springer – Verlag Inc.
Hogg, R., Craig, A., and McKean, J. (2004). An Introduction to Mathematical Statistics. Prentice Hall.
Jagadish, H.V., Gehrke, J., Labrinidis, A., Papakonstantinou, Y., Patel, J.M., Ramakrishnan, R. and Shahabi, C., 2014. Big data and its technical challenges. Communications of the ACM, 57(7), pp.86-94.
Kalyvas, J.R. and Albertson, D.R., 2015. A big data primer for executives. Big data: a business and legal guide. CRC Press, Boca Ratón Google Scholar.
Liese, F. and Miescke, K. (2008). Statistical Decision Theory: Estimation, Testing, and Selection. Springer.
Pearl, J. (2000). Casuality: models, reasoning, and inference. Cambridge University Press.