Difference between revisions of "ANLY482 AY2017-18T2 Group18/TeamDAcct Scope"
Zqlow.2014 (talk | contribs) |
Zqlow.2014 (talk | contribs) |
||
| Line 52: | Line 52: | ||
<div style="border-style: solid; border-width:0; background: #0000cd; padding: 7px; font-weight: bold; text-align:left; line-height: wrap_content; text-indent: 20px; font-size:20px; font-family:Century Gothic;border-bottom:5px solid white; border-top:5px solid black"><font color= #ffffff> General Scope</font></div> | <div style="border-style: solid; border-width:0; background: #0000cd; padding: 7px; font-weight: bold; text-align:left; line-height: wrap_content; text-indent: 20px; font-size:20px; font-family:Century Gothic;border-bottom:5px solid white; border-top:5px solid black"><font color= #ffffff> General Scope</font></div> | ||
<div style="background: #ffffff; text-align:left; line-height: wrap_content; text-indent: 0px; font-size:16px; font-family:Century Gothic"><font color= #000000> | <div style="background: #ffffff; text-align:left; line-height: wrap_content; text-indent: 0px; font-size:16px; font-family:Century Gothic"><font color= #000000> | ||
| − | |||
The steps in detail are as follow: | The steps in detail are as follow: | ||
Revision as of 10:11, 14 January 2018
| Home | About Us | Project Overview | Project Findings | Project Management | Documentation | ANLY482 Homepage |
The steps in detail are as follow:
Problem Identification: To sit down with client and discuss about the business problems that need to be solved. Thereafter to identify the pertinent business issues/questions that the company is currently facing.
Data Preparation: To acquire/collect, clean, transform and integrate data (ETL) into a suitable form for further analysis.
Data Exploration: To perform exploratory data analysis (EDA) to analyse the data sets to summarise their main characteristics.
Insights Discovery: From uncovering patterns, trends in data through data exploration, to form insights and make actionable recommendations/responses in model selection. This allows us to better focus analytical efforts into variables/areas related to the business issues identified.
Model Selection: To come up with models based on the type of business issues/questions identified.
Model Validation: To estimate model performance by verifying sensitivity analyses between actual and predicted outcomes.
Model Development: To choose the most suitable model after validation is done and test it against new data we have on hand.
Communication of Results: To communicate to the client and illustrate key insights contained in the data analysed using visualization tools.
