Difference between revisions of "G7 Dashboard"

From Analytics Practicum
Jump to navigation Jump to search
Line 78: Line 78:
  
 
</font>
 
</font>
 +
<br>
 +
<font color = "#ED515C" face= "Century Gothic" size=16px>
 +
Flight Type Analysis
 +
</font>
 +
<br>
 +
[[Image:DHL_Dash2.png|center|1300x320px]]

Revision as of 16:17, 15 April 2018

DHL Common Banner.png

HOME

 

PROJECT OVERVIEW

 

ANALYSIS & FINDINGS

 

PROJECT MANAGEMENT

 

ABOUT US

 

PRACTICUM HOMEPAGE

 

Note: Due to the confidential nature of our project, we will not be able to reveal all the missing values/fields on this wiki.

With our Confirmatory Analysis, we can be certain that the operational performance is different across different BUs and across different Flight Types. But this analysis was done for the entire data set on a broad level. We can possibly get more insights if we can go in further depth and analyze for specific lanes during specific time periods. To achieve this, the team came up with a Dashboard consisting of a combination of conventional visualizations like stacked bar graphs and non-conventional visualizations like Mosaic plot and Box plots to visualize the operational performance across different BUs and for different Flight types. The flexibility of this dashboard will give GAMs a more comprehensive and easy to understand view of the operational performance.
Business Unit Analysis

DHL Dash1.png

The following is a breakdown of the different parts of this dashboard:

1. Firstly, the layer of filters on top allows the Sponsor to filter data used to generate the graphs according to:

  • Lane Pair
  • Date Range across the three years of provided data
  • Years
  • Months

2. A summary table on the top right to show overall performance (Delayed vs On-Time percentage) of a specific lane.

3. A mosaic plot measuring the percent of ‘Delayed’ vs ‘On Time’ shipments across different BUs. In this, the light blue layer represents ‘On Time’ shipments, while the dark blue layer represents ‘Delayed’ shipments. The width of each box in the Mosaic rectangle shows how big each BU is in terms of total number of shipments for that lane. This visualization will help understand the true performance of a lane as GAMs can focus only on the performance of BUs with large widths since they account for the bulk of shipments.

4. Since we cannot use mean as a point estimator for delay days, we use a box plot visualization on the bottom left which displays the entire distribution of delay days across different BUs. The black line represents the median and the dot represents the mean.

5. Tables on the bottom right displaying the average number of days and the median number of days taken for each journey leg of a shipment, broken down by BUs.

Example of insight drawn: In the screenshot above, it can be derived that for the last three years, for the lane from Cincinnati (CVG) to Paris (PAR), BU 4 accounted for the most number of shipments, with 80.52% of them on time, with an average of 3.08 days for the entire DTD journey. The most number of days were taken in ATA. The box plot shows that the median number of days by which the shipment was delayed is 1 day.


Flight Type Analysis

DHL Dash2.png