A Data Analysis

This report’s goal is to assess business performance metrics for the company and provide the best graphical representation of the data. The thirteen spreadsheets were all taken into account for this report, together with their sources, measures, and suggestions for the best graphical representation (Victoria Business School, 2016)

The scatter with straight lines and markers chart, clustered column line combination chart, and line chart are suggested as the finest charts to be utilized for the primary review after carefully evaluating the spreadsheets and taking all factors into account. The main purpose of this report is to examine data collected quarterly and monthly in order to determine the best methods to represent the data. The report will also dwell on the specific measures of the available data.

Scope

While analyzing the data, it was important to consider its suitability for corporate use, warranties and optional benefits.

Method

The data to be examined was collected on a monthly or quarterly basis from the company. The task is to verify the data is from internal sources, external sources or from special sources.(Thompson, 2005)Measures of the data are also to be determined together with the kind of graph fit for the data.

Background Information

Fast Technologies is a company that manufacturers’ solid states drives (SSD) used for desktops and laptops. The SSD’s are distributed to the users through dealers which are located in different continents of the world. Fast Technologies has its manufacturing base in Atlanta with several other plants in other different locations. The company has a total employee count of 2500 from all the plants. The main markets of their products include United States, North America, South America, Asia, Europe and Middle East.

Findings

Dealer satisfaction data is categorical. In this dataset, the variables are measured on a scale (1=poor, 2=less than average, 3=average, 4=above average and 5= excellent). The data is from internal reports of the organization. The best chart that I would recommend for this data is clustered column line combination chart or a clustered column chart. A clustered column chart is used to compare values across a few categories while a clustered column-line combination chart is used to emphasize different types of information. It can be used in a wide range of values hence suitable for this kind of data.

End-user satisfaction data is also categorical. It is on the same scale as the dealer satisfaction; (1=poor, 2=less than average, 3=average, 4=above average and 5= excellent). The data is from internal sources. The best chart for this type of data is a clustered column-line combination chart. This is because the chart will be able to show and emphasize on the different types of information in this dataset. For this type of categorical data, this would be useful.

Customer survey 2016 represents ratings from the customers on specific qualities of the SSD. The attributes are speed, price, reliability and service. This data is categorical for the attributes are rated on a scale of 1-5. The best chart for this data is either a stacked bar chart or a clustered column chart. A stacked bar chart will be able to compare parts of the whole dataset across categories. A clustered column chart can be used to compare the values across given categories. The data is from internal sources.

Complains dataset is numerical. It shows the exact number of complaints registered by customers each month in the five regions where Fast Technologies is located. Origin of the data is from internal reports of the company. The best chart that can be used to represent the data is a clustered column-line combination chart or a stacked column chart. The stacked column chart can be used to compare parts of a whole while the clustered column-line combination chart will be used to display different types of information and show the trend using the line on the chart.

Fast 1000 and 2000 GB sales datasets are numerical. They provide the number of sales of the product for different regions. The data is from internal sources, data collected from the different regions over the past five years. The best chart for these datasets is a line chart. A line chart will display trends over time. The datasets have order in form of months which is appropriate with this type of chart.

Industry 1000 and 2000 GB total sales dataset is numerical. It shows list of number of units sold by all producers in terms of regions. The data is internal since it was collected from regional plants. The best chart for these datasets is a line chart or a clustered column line chart. The chart will emphasize on the information and also show the trend of the dataset.

Unit production costs dataset is numerical. The data is from survey conducted within the manufacturing plants. It displays data of monthly accounting estimates of the variable cost per unit for manufacturing 1 and 2 TB SSD’s. The best chart for this data is a line chart. The line chart will be able to display trends over time. The dataset is ordered in months hence the line chart will clearly show the trends.

Operating and interest expenses dataset is numerical. It provides monthly administrative, depreciation and interest expenses at a corporate level. The data is collected internally. The best fir chart for this data is a scatter with straight lines and markers chart. This chart will be able to show comparison among the datasets and can also represent separate measurements.

On time delivery dataset is numerical. This data shows the number of deliveries made each month from Fast Technologies major suppliers, the number of time and the percent on time. The data is from an internal source since it involves the company. The best chart for this dataset is a clustered column line combination chart. The chart will emphasize on the different monthly information. The lone will be used to show the trend on the number off deliveries.

The defects-after-delivery dataset is numerical. The best chart for this data is a stacked column chart. The chart will be used to show varied comparisons of the whole data and the whole change over the twelve months. The data is from internal sources.

Time to pay suppliers dataset is numerical. It provides data on the measurements in days from the time invoice is received until when the payment is sent. The best chart for this dataset is scatter with straight lines and a markers chart. The data has two variables hence this chart will be suitable to compare the two sets of values and show the trend in between. The data was collected internally.

Response time dataset is numerical. This data gives the time taken by Fast Technologies customer service personnel to respond to service calls by quarter. The best chart for this data is a stacked column chart. It will be used to draw comparisons and how the segments change over time.

Employee satisfaction is categorical. Has surveys done internally over the past four years which determine the overall satisfaction with their jobs on a scale. The best chart for this data is a clustered column-line combination chart. It will be able to display the range of scales over time.

I TB SSD production time is numerical. The best chart for this data is a scatter with straight lines and markers chart. It will be able to compare the two sets of values in the datasets. The data is from special sources.

1 TB SSD Test is categorical, qualitative data. This data will be best represented by a stacked area chart. It will be used to display the relationship of parts to whole over the given time and categories. It will be able to show the magnitude of the change over time. This data is from special sources.

Employee retention is a mix of both categorical and numerical data. The best chart for this dataset is a clustered column chart which is used to compare values across categories. In this case it will be a good match for a mix of both numerical and categorical data.

Purchasing survey data is numerical. The data was collected from special sources. The best chart for this data is a stacked column chart. It will be able to compare the parts of the whole data over time.

Conclusions and recommendations

After reviewing the datasets, it was found that the data was from either internal or special sources. The measures used in the datasets were varied, some were categorical others were numerical. The most common chart that I would recommend is scatter with straight lines and markers chart, clustered column line combination chart and a line chart. This is because, the review was to oversee production operations over a given time period. Using graphs with lines will help determine the trend on a given period of time.

References

Evans, J. R. (2013). Business analytics: Methods, models, and decisions (Vol. 3). Upper Saddle River, NJ: Pearson.

Thompson, A. (2005). Guide to Business Report Writing. Entrepreneurship and Business Innovation: The Art of Successful Business Start-Ups and Business Planning, 163-73.

Victoria Business School. (2016, March). How to write a business report. Retrieved from University of Wellington/Victoria: http://www.victoria.ac.nz/vbs/teaching/resources/VBS-Report-Writing-Guide-2016.pdf