Business Analytics And Decision Making: A Case Study
Objective
Business Analytics refers to a study of data based on the statistical analysis and operations analysis, which helps to form the predictive models, helps the companies in automating and optimizing their business processes and communicates the results with the customers and the business partners. Additionally, the data-driven companies make use of Business Analytics for achieving competitive advantage, with its insight for supporting the evidence-based decision making and performance management.
Here is a case study which ensures to enlighten about the Business Decision Analytics, where I am a member of the team with three line mangers for forming a panel with the task of business cost containment in an organisation which contains 300 people. The importance and urgency of the panel’s work relates to the business which has recently lost two key products from its product line. The reason behind this is considered as the changes in the government policy, which needs immediate step to stop the falling business profitability.
Thus, this case requires comparing, contrasting and critically evaluating the sources of data, for making the right decisions in a range of business contexts. The decision making systems and techniques should be examined and evaluated, to analyze the sustainable outcomes. The emerging tools and technologies for decision making must also be examined. Because, the business has come to a conclusion that it instantly requires to decrease its wage and salary costs, for surviving the next period. Hence, the executive management has taken a decision of setting up a panel for advising on methods to instantly decrease its wage and the salary costs, by decreasing the number of staff, to positively address the issues with the business’s current P&L statement.
On the other hand, the business is well aware of the amount of staff required for the business, to run the business, i.e., it believes that it needs 275 staff for operating its business well. Strong recommendations are demanded by the team with appropriate justifications on given for how to keep the profits up, without firing 60 percentage of staff or by firing small percentage of staff.
Objective
The objective of this report includes, the sources of data will be compared, contrasted and critically evaluated. The decision making systems and techniques will be examined and evaluated. The emerging tools and technologies for decision making will be critically examined. To recommend and justify how to keep the profits up, without firing 60 percentage of staff or by firing small percentage of staff.
1. Main Discussion
1.1 Problem Definition
The importance and urgency of the panel’s work relates to the business which has recently lost two key products from its product line. The reason behind this is considered as the changes in the government policy, which needs immediate step, to stop the falling business profitability. The decided solution is decreasing the number of staff in the company. Here, the problem is to look for the right staff to be terminated based on positive addressing, instead of randomly removing the employees. It is a serious and complex task to carry out. Thus, the team requires analyzing the provided data set to list the people recommended for redundancy. Totally, out of 60 people, the team needs to select the people and provide appropriate recommendations on the type and number of people to be made redundant (Dasgupta, 2015).
Main Discussion
The main problem here is, how to keep the profits up, without firing 60 percentage of staff or by firing small percentage of staff. Then what else can be the solution.
1.2 Situational Analysis
The current situation of the business is that it has come to a conclusion that, it instantly requires to decrease its wage and the salary costs, for surviving the next period. The executive management has taken a decision of setting up a panel for advising on methods to instantly decrease its wage and salary costs, by decreasing the number of staff, to positively address the issues with the business’s current P&L statement. The team is asked to use the available data set and analyse it for providing a list of people for redundancy (Delen, 2015).
The case study provides the exposure of experiencing to work at both the individual level as well as a team member, for identifying the data from different sources and contexts to process the information and help in decision making. On the other hand, it also helps to form a group for sharing the MBTI results, decision preferences and other types of psychometric tests that could support the team in identifying and acting on the differences between each individual’s information preferences, abilities, decision styles and willingness to work in the team.
Additionally, to work as a team member to recognize the differences in the preferences of information processing, ways of working together and decision styles, by engaging the team in data evaluation, information processing, utilizing the systems of decision-making and techniques for instant and high quality group decisions.
1.3 Sense Making
To make the decisions for the provided case study problem by using the business analytics tool like Weka. So, user needs to download and install the weka. After, open the provided dataset like access data. Then, perform the business analysis (Getting started with business analytics: insightful decision-making, 2013).
The provided data set is successfully opened and it is illustrated as below.
After, choose classify to analysis the provided the data. Here, we are choose the years of experience to predicted the employee’s information to reduce the employee salary or removed from the job.
1.4 Formulation of potential solutions
Practical Business Analysis one by using the Random Tree for Years of experience
To make the decisions for the provided case study problem by using the business analytics tool like Weka. So, user needs to download and install the weka. After, open the provided dataset like access data. Then, perform the business analysis.
The provided data set is successfully opened and it is illustrated as below (Isson and Harriott, 2013).
After, choose classify to analysis the provided the data. Here, we are choose the years of experience to predicted the employee’s information to reduce the employee salary or removed from the job.The below screenshots is used to display the random tree analysis on years of experience variables (Liebowitz, 2014).
Output is shown below.
RandomTree
==========
Name = Jacob : 10 (1/0)
Name = Michael : 2 (1/0)
Problem Definition
Name = Mary : 7 (1/0)
Name = Joshua : 6 (1/0)
Name = Youseff : 1 (1/0)
Name = Emma : 3 (1/0)
Name = Abe : 2 (1/0)
Name = Kelvin : 7 (1/0)
Name = Lillian : 11 (1/0)
Name = Terry : 10 (1/0)
Name = Rubin : 6 (1/0)
Name = Hassan : 7 (1/0)
Name = Fred : 6 (1/0)
Name = Shavonne : 8 (1/0)
Name = Sibyl : 9 (1/0)
Name = Larry : 1 (1/0)
Name = Zane : 5 (1/0)
Name = Rudolph : 1 (1/0)
Name = Angelo : 3 (1/0)
Name = Lee : 5 (1/0)
Name = Marc : 5 (1/0)
Name = Chad : 7 (1/0)
Name = Anton : 12 (1/0)
Name = Rick : 11 (1/0)
Name = Keith : 1 (1/0)
Name = Torri : 1 (1/0)
Name = Mica : 3 (1/0)
Name = Kim : 4 (1/0)
Name = Earle : 3 (1/0)
Name = Hester : 8 (1/0)
Name = Lindsey : 7 (1/0)
Name = Mario : 8 (1/0)
Name = Simon : 8 (1/0)
Name = Kathrine : 9 (1/0)
Name = Stephen : 4 (1/0)
Name = Blake : 3 (1/0)
Name = Fraser : 13 (1/0)
Name = Gemma : 5 (1/0)
Name = Heath : 6 (1/0)
Name = Rashid : 7 (1/0)
Name = Mohammad : 9 (1/0)
Name = Nada : 9 (1/0)
Name = Paul : 6 (1/0)
Name = Sarah : 4 (1/0)
Name = Nima : 5 (1/0)
Name = David : 5 (1/0)
Name = Ali : 9 (1/0)
Name = Maria : 8 (1/0)
Name = Nicola : 8 (1/0)
Name = Lorenzo : 2 (1/0)
Name = Colin : 1 (1/0)
Name = Bryan : 1 (1/0)
Name = Vito : 9 (1/0)
Name = Rosa : 4 (1/0)
Name = Yvette : 6 (1/0)
Name = Marcel : 9 (1/0)
Name = Claude : 13 (1/0)
Name = Louis : 2 (1/0)
Name = Pam : 1 (1/0)
Name = Percy : 7 (1/0)
Size of the tree : 61
Time taken to build model: 0 seconds
=== Cross-validation ===
=== Summary ===
Correlation coefficient 0.1425
Mean absolute error 2.7234
Root mean squared error 3.411
Relative absolute error 98.3241 %
Root relative squared error 102.126 %
Total Number of Instances 60
Ignored Class Unknown Instances 6
The years of experience has the 60 instances and Ignored class unknown instances are 6.
Practical Business Analysis one by using the Random Tree for Employees Position
Size of the tree : 204
Time taken to build model: 0 seconds
=== Stratified cross-validation ===
=== Summary ===
Correctly Classified Instances 28 44.4444 %
Incorrectly Classified Instances 35 55.5556 %
Kappa statistic 0.009
Mean absolute error 0.2097
Root mean squared error 0.3548
Relative absolute error 96.1205 %
Root relative squared error 108.6119 %
Total Number of Instances 63
Ignored Class Unknown Instances 3
=== Detailed Accuracy By Class ===
Situational Analysis
TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class
0.071 0.163 0.111 0.071 0.087 -0.109 0.580 0.260 S
0.727 0.767 0.511 0.727 0.600 -0.045 0.470 0.494 M
0.231 0.040 0.600 0.231 0.333 0.286 0.717 0.373 J
0.000 0.000 ? 0.000 ? ? 0.069 0.015 Safe no accidents
0.000 0.016 0.000 0.000 0.000 -0.016 0.100 0.015 Moderately safe:1 near miss reported
0.000 0.016 0.000 0.000 0.000 -0.016 0.108 0.015 Safety Risk – Has been in 1 accident event
Weighted Avg. 0.444 0.447 ? 0.444 ? ? 0.527 0.394
=== Confusion Matrix ===
a b c d e f <– classified as
1 13 0 0 0 0 | a = S
5 24 2 0 1 1 | b = M
3 7 3 0 0 0 | c = J
0 1 0 0 0 0 | d = Safe no accidents
0 1 0 0 0 0 | e = Moderately safe:1 near miss reported
- 1 0 0 0 0 | f = Safety Risk – Has been in 1 accident event
Practical Business Analysis one by using the Gaussian Processes for Years of experience
Kernel used:
Linear Kernel: K(x,y) = <x,y>
All values shown based on: Normalize training data
Average Target Value : 0.40694444444444444
Inverted Covariance Matrix:
Lowest Value = -0.14609951610422994
Highest Value = 0.35795999121679684
Inverted Covariance Matrix * Target-value Vector:
Lowest Value = -0.13502653684508972
Highest Value = 0.16806340316705135
Time taken to build model: 0.04 seconds
=== Cross-validation ===
=== Summary ===
Correlation coefficient 0.4637
Mean absolute error 2.416
Root mean squared error 2.96
Relative absolute error 87.2256 %
Root relative squared error 88.6244 %
Total Number of Instances 60
Ignored Class Unknown Instances 6
Annual Salaries for Employees
1.5 Selection between solution
Based on experience and position analysis on Weka, it is used to predict the employee’s information to remove from the job. In years of experience, the below two years are needs to remove from the job because these does not have any knowledge about the business process and also verifies the position level as junior level with below two years of experiences (Miller, 2015).
1.6 Decision making based on solutions
Decision making based on the solutions is to remove the junior level with below two years of experiences. Because, junior specialists can some of the time saddle their vitality to impel the association forward; in any case, they as a rule need both the expert and educational experience expected to roll out a positive improvement. More seasoned laborers have this experience and are frequently overlooked resources for some organizations. More youthful laborers regularly battle to push ahead a reliable way (Ohri, 2013). Despite their insight and brilliant thoughts, they were not able make their dreams work out as intended. The issue was they continually altered their opinions and were not able propel the business a reliable way.
While a few representatives might have the capacity to instantly re-organize their time and undertakings, some may at first experience troubles getting balanced with their new duties. The expansion in work can make representatives get baffled, wore out and bring down their general profitability while others perform ineffectively, because of absence of preparing, absence of intrigue or absence of clearness about their new assignments. Poor execution can make representatives feel a feeling of inadequacy or as though they’ve you thumped. Poor execution can likewise make workers get deprived of their new obligations, which can cause humiliation (Power and Heavin, 2017).
1.1 mplementation of decisions
Implementations of decisions is used to increase the productivity. The business urgently requires a board, for talking about the business which has as of late lost two key items from its product offering. The purpose for the misfortune is the adjustments in the administration approach, which needs quick advance, to stop the falling business gainfulness. Henceforth, diminishing the quantity of staff is considered as the arrangement, to emphatically address the issues relying upon the business’ present P&L declaration. Along these lines, the group is requested to utilize the accessible informational index and break down it for giving a rundown of individuals to repetition.
From now on, in this report, the wellsprings of information are thought about, differentiated and fundamentally assessed, for taking right choices in a scope of business settings, then, the basic leadership frameworks and methods are inspected and assessed, for breaking down the practical results. Further, developing apparatuses and innovations for basic leadership are fundamentally inspected (PUTLER, 2017).
2. Recommendations
A standout amongst the most significant advantages of employee’s analysis is that you’re ready to robotize such huge numbers of procedures that can uncover essential insights about the work propensities for your group. These procedures may appear to be minor when watched independently, however exhaustively they can have a colossal effect. Accept timecard management for instance. In isolated conditions, taking a look at a solitary worker’s timecard information and efficiency levels might possibly give experiences into how that individual could best be used (Surma, 2011). Be that as it may, when this information is gathered progressively for a whole office, examination can show imperative patterns concerning how time administration impacts profitability. This process is used to improve the business productivity.
3. Conclusion
A case study is considered in this report which reviews the aspects of business decision analytics. The current situation in the case study includes a business which has come to a conclusion of instantly decreasing its wage and the salary costs, in order to survive the coming year. To take this action, the executive management has taken a decision of setting up a panel for advising on methods to instantly decrease its wage and salary costs.
The case study has helped to understand the importance of Business Decision Analytics, where I am a member of the team with three line mangers for forming a panel with the task of business cost containment in an organisation which contains 300 people. The business urgently requires a panel, for discussing the business which has recently lost two key products from its product line. The reason behind the loss is the changes in the government policy, which needs immediate step, to stop the falling business profitability.
Hence, decreasing the number of staff is considered as the solution, to positively address the issues depending on the business’s current P&L statement. Thus, the team is asked to use the available data set and analyze it for providing a list of people for redundancy.
Henceforth, in this report, the sources of data are compared, contrasted and critically evaluated, for taking right decisions in a range of business contexts, Then, the decision making systems and techniques are examined and evaluated, for analyzing the sustainable outcomes. Further, emerging tools and technologies for decision making are critically examined.
To accomplish this, the cases study gives the exposure of experiencing to work at both the individual level as well as a team member, for identifying the data from different sources and contexts to process the information and help in decision making. On the other hand, it also helps to form a group for sharing the MBTI results, decision preferences and other types of psychometric tests that could support the team in identifying and acting on the differences between each individual’s information preferences, abilities, decision styles and willingness to work in the team. Additionally, to work as a team member to recognize the differences in the preferences of information processing, ways of working together and decision styles, by engaging the team in data evaluation, information processing, utilizing the systems of decision-making and techniques for instant and high quality group decisions.
Therefore, appropriate justifications given for how to keep the profits up, without firing 60 percentage of staff or by firing small percentage of staff.
References
Dasgupta, M. (2015). Analytics for Decision Making at Ports. International Journal of Business Analytics and Intelligence, 3(2).
Delen, D. (2015). Real-world data mining. Upper Saddle River, NJ: Pearson Education.
Getting started with business analytics: insightful decision-making. (2013). Choice Reviews Online, 50(12), pp.50-6856-50-6856.
Isson, J. and Harriott, J. (2013). Advanced business analytics. Hoboken, N.J.: John Wiley & Sons.
Liebowitz, J. (2014). Business analytics. Boca Raton, Fla.: CRC Press.
Miller, T. (2015). Modeling techniques in predictive analytics. Upper Saddle River, NJ: Pearson Education.
Ohri, A. (2013). R for Business Analytics. New York, NY: Springer New York.
Power, D. and Heavin, C. (2017). Decision Support, Analytics, and Business Intelligence, Third Edition. New York: Business Expert Press.
PUTLER, D. (2017). CUSTOMER AND BUSINESS ANALYTICS. [S.l.]: CRC PRESS.
Surma, J. (2011). Business intelligence. [New York, N.Y.] (222 East 46th Street, New York, NY 10017): Business Expert Press.