Tenhagen_DAT-510_Final_Project_Milestone_2

docx

School

Southern New Hampshire University *

*We aren’t endorsed by this school

Course

510

Subject

Business

Date

Feb 20, 2024

Type

docx

Pages

4

Uploaded by SargentGuanacoMaster291

Report
Ted Tenhagen DAT-510-R5311 Milestone 2: Sections A - D September 17th, 2021
Proposal A.) Goals The main goal that Richard is looking to accomplish through Data Analytics is to increase the number of customers who are purchasing the new eReader that is being released by his employer. While there are a large number of customers who already plan on purchasing the eReader, the real target customers are those who were either late to purchasing the previous eReader or didn’t make the purchase at all. By isolating buying patterns that may have led the previous customers to make the purchase and seeing if there are similar buying patterns in those who didn’t, the marketing department can more accurately make decisions about where to place advertisements or create incentives to purchase the newest eReader. B.) Data Analytics Life Cycle The data analytics life cycle applies to this problem in the following ways (Sharma 2021): 1.) Data Discovery and Information - Reviewing the previous sales data can help to reveal any critical purchasing decisions from the customers that made the purchase of the previous generation of the eReader. 2.) Data Preparation and Processing - The data that was given to Richard by his employer is not as detailed as an analyst would want since the data only shows if the consumer made purchases from certain product categories and what their browsing habits are. If we would be able to obtain the last 20 - 30 purchases made by the consumer, Richard could make a more accurate prediction about which products influence the purchase of the eReader.
3.) Design a Model - Using the ETLT model would make the most sense for this problem since ideally, Richard would pull the more detailed data from the company’s server, filter out any irrelevant information like the details of what the purchased products are and instead put them into product categories, load the now filtered data into R, and then manipulate the data to determine at which point the marketing team should insert promotions. 4.) Model Building - By determining the density of the product categories that were sold and how long the purchases were made before the consumer purchased the eReader, the critical products that influenced the consumer to make the initial purchase would become more apparent. 5.) Result Communication and Publication - Once the model has been created and the critical purchase items are determined, Richard would then present the model to the marketing team and show that the critical purchases were made close to the purchase of the previous generation eReader. The information in the presentation would help to back up the findings but would need a substantial amount of the consumers to have the ‘critical’ purchase shortly before the eReader purchase and that it wasn’t just a purchase made on its own with no influence on the purchase of the eReader. 6.) Measuring of Effectiveness - To determine how effective the implementation of the promotions and advertisements would be, the marketing team could create a promo code or tracking CTR on the advertisements that were placed on the product pages of the critical purchase albums and then compare the sales data of both products and then see the amount of time between the ‘critical’ purchase and the eReader. In this scenario, the
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
shorter the time period between the critical purchase and the eReader would result in a more successful implementation. C.) Value of Life Cycle After following the process laid out by the data analytics life cycle above, Richard will be able to more effectively use the data collected by his employer to help them make the decision on the best products and promotions to use in order to increase the number of purchases made for the new eReader. D.) Data After reviewing the data that was provided by the employer, the data does leave a lot to be wanted. The data does not show what the previous purchases were before the eReader was purchased, only that the consumer purchased products in different categories in the past 12 - 18 months. If we were able to obtain the previous 10 product purchases that were made by each consumer to see if there were any products that were more likely to lead the consumer to purchase the eReader. The more detailed the data would be, the more accurate of a prediction Richard would be able to make for the marketing team. Sources North, M. A. (2012). Data Mining for the Masses. Sharma, R. (2021, September 15). 6 phases of data analytics lifecycle every data analyst should know about . upGrad . Retrieved October 3, 2021, from https://www.upgrad.com/blog/data-analytics-lifecycle/.