Entry Name: "UBA-Alcoser-MC2"

VAST Challenge 2014
Mini-Challenge 2

Team Members:

Jorge Luis Alcoser Flores, Universidad Cesar Vallejo (Peru), jl.tauro.88@gmail.com Primary
Fredy Hernan Gomez Lopez, Franciso Jose de Caldas Bogota - Colombia, dygomez@gmail.com
Miguel Francisco Jarma Forero, Universidad del Magdalena - Colombia, mjarma83@gmail.com

Student Team: YES

Analytic Tools Used:

Tableau, Excel, Sql Server 2012,Spss,Qgis

Approximately how many hours were spent working on this submission in total?

Our team spend 56 hours working on the challenge

May we post your submission in the Visual Analytics Benchmark Repository after VAST Challenge 2014 is complete? YES

Video:

Youtube: UBA-Alcoser-MC2_Video

Download: UBA-Alcoser-MC2_Video

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Questions

MC2.1 – Describe common daily routines for GAStech employees. What does a day in the life of a typical GAStech employee look like? Please limit your response to no more than five images and 300 words.

To find the daily routines for the Gastech employees we make a correlation analysis and find the next results

• It can be seen that we obtain a inertial of 0.84 with 2-dimensional which allows us to say that these two dimensions explain up to 84% of the total variance of the data.

• From the pictures we can see that the transactions with higher values are made by employees of facilitie type, and they were done in weekdays.
• These purchases do not have a degree of loyalty in the store, they do not have loyalty cards.
• The volume of transactions is carried higher price in local as kronos pipe and make matters worse, abila airport, etc..
• At locations ranging as employee profiles are differentiated between facilities and others, Engineer, information tecnology and some exceutive, you share many common locations where they conduct their transactions.
• But you can also see places to Executivos differential and security personnel.
• Most relationship between these variables was observed between the type of employee and the location where the transaction takes, so you can differentiate types of employees usually get to locations.

• This image show the most frecuent places that the gastech employees goes during the week

• This image show the daily routine of the gastech employees by area

• This image shows the number of people who frequent a place at certain times of day

• this picture describes the movement of an employee where the day begins at the points of light blue and ends in the dark blue points.

MC2.2 – Identify up to twelve unusual events or patterns that you see in the data. If you identify more than twelve patterns during your analysis, focus your answer on the patterns you consider to be most important for further investigation to help find the missing staff members. For each pattern or event you identify, describe

Evente No.1

• a. What is the pattern or event you observe? a spend of 10000
• b. Who is involved? lucas alcazar
• c. What locations are involved? frydos autosupplay n´more
• d. When does the pattern or event take place? 13/01/2014
• e. Why is this pattern or event significant? because the spending is rare and it exceeds the average of the normal expenses of employees
• f. What is your level of confidence about this pattern or event? Why?

Evente No.2

• a. What is the pattern or event you observe? that there are 3 person of diferent area meet at the same place
• b. Who is involved? lucas alcazar, ada campos correntes, Varja Lagos
• c. What locations are involved? kronos market
• d. When does the pattern or event take place? 19/01/2014
• e. Why is this pattern or event significant? because the spending is rare and it exceeds the average of the normal expenses of employees
• f. What is your level of confidence about this pattern or event? Why?

Evente No.3

• a. What is the pattern or event you observe? We see two groups of employees who are at different places but there a single employee relations in common that makes both groups
• b. Who is involved? albina hafon
• c. What locations are involved? Ouzeri Elian
• d. When does the pattern or event take place? dont have the date in the analisis but is close to the 16/01/2014
• e. Why is this pattern or event significant? beacuse there is an employee that tries to meet everyone of gastech
• f. What is your level of confidence about this pattern or event? Why?

MC2.3 – Like most datasets, the data you were provided is imperfect, with possible issues such as missing data, conflicting data, data of varying resolutions, outliers, or other kinds of confusing data.  Considering MC2 data is primarily spatiotemporal, describe how you identified and addressed the uncertainties and conflicts inherent in this data to reach your conclusions in questions MC2.1 and MC2.2. Please limit your response to no more than five images and 300 words.

The problems we encounter when analyzing the data were:

• Redundancy data
• Missing Values
• Conflicting data
• Outliers

GPS data was reduced by taking only the data of latitude and longitude, reducing it to the minimum length in minute and hour specified. We unify the Transactions of LOYALTY_DATA and CC_DATA tables with records that were identified as the same transaction and creating a variable for whether loyalty card is presented when they made the transaction. Other thing we do to reduce the data was a join between the tables cars_assigment and credit_card transaction to see the car location of the different employees, with their transactions, this was done by first name and last name, and hour of the transactions.

To complement the missing values of the varibles CURRENTEMPLOYMENTTYPE, CURRENTEMPLOYMENTTITLE we used employees records file of the minichallenge1

After performing a deeper analysis of the data we found an outlier which gives us a step to think about doing other types of analysis

We made a join between the transaction date and the GPS date, to have an specific idea of a record in a given time, gps location, location, employee and Price.