Difference between revisions of "ANLY482 AY2017-18T2 Group01: Project Management"
| Line 48: | Line 48: | ||
[[File:Data prep.png|700 px|centre|]] | [[File:Data prep.png|700 px|centre|]] | ||
| + | |||
| + | ''Joining the Dataset'' : We combined the three sheets into one consolidated sheet. | ||
| + | |||
| + | ''Developing Meta-Data'': Once we had our combined sheet ready, we developed the meta-data to clearly understand the variables and their distributions. We had to undertake the following steps: | ||
| + | <br> i. Categorize the variables: We first had to categorize the variables into Numeric vs. Character Variables, and then further divide the Numeric variables into nominal, ordinal and continuous variables. | ||
| + | <br> ii. Map Variable Distribution: We then mapped the distribution of each variable, to find the reliability and steps needed for cleaning. | ||
| + | |||
| + | ''Cleaning and Standardisation'' : Here we looked into missing values, insignificant values, discrepancies and binning. | ||
| + | |||
| + | ''Transformation'': We developed a cleaned master sheet, and separate vendor and user sheets for more meaningful analysis | ||
Due to confidentiality, we cannot share data details. For more information, please refer to our e-learn drop box or email us. | Due to confidentiality, we cannot share data details. For more information, please refer to our e-learn drop box or email us. | ||
Revision as of 22:10, 25 February 2018
Step 1:
Understanding the Business Problem and Business Context:
We first wanted to gather all information related to the booking journey of customers and the key influencing factors. To do this we carried out the following steps:
1. Spoke with eatigo employees beyond our sponsor (Sales Lead and Marketing Lead)
2. Interviewed eatigo customers to understand their typical priorities and their customer journey.
Based on our understanding, we have mapped out the customer journey map as follows:
Step 2:
Data Preparation: The next step involved zooming into the data sheets provided to us and understand each variable, it's sufficiency and relevance in helping us solve the business problem, and then preparing it for analysis. These were the steps in Data Preparation:
Joining the Dataset : We combined the three sheets into one consolidated sheet.
Developing Meta-Data: Once we had our combined sheet ready, we developed the meta-data to clearly understand the variables and their distributions. We had to undertake the following steps:
i. Categorize the variables: We first had to categorize the variables into Numeric vs. Character Variables, and then further divide the Numeric variables into nominal, ordinal and continuous variables.
ii. Map Variable Distribution: We then mapped the distribution of each variable, to find the reliability and steps needed for cleaning.
Cleaning and Standardisation : Here we looked into missing values, insignificant values, discrepancies and binning.
Transformation: We developed a cleaned master sheet, and separate vendor and user sheets for more meaningful analysis
Due to confidentiality, we cannot share data details. For more information, please refer to our e-learn drop box or email us.
Step 3:
Model Preparation: We plan to use clustering, market basket analysis and geospatial methods to derive our final clusters and recommendations. We are currently working on this.
Step 4:
Analysis and Insights: Based on our insights we will be developing a recommendation plan for Eatigo which will enable the company to increase bookings
We have prepared a work plan for our project as follows.
[Our discussions with the sponsor, professor and amongst ourselves ]
