Your task is to produce a data science proposal that discusses the possibility of automatically predicting the “sales of a product.” The length of the report should not be more than 10 pages, including the title page and the reference page (single line space; 11pt font; Arial). Table of Content is not required. There are 100 marks in this assignment. Your proposal must address the following tasks. 1. The file Assignment1_BigMart_Data.csv (available on Canvas) a dataset of 1,559 products across 10 stores in different cities. The description of the dataset is provided in the appendix. Use the following steps to formulate appropriate hypotheses about the expected outcomes from the analysis of the dataset: a. Clean the dataset to remove/patch the missing records/values and record all changes. b. Identify the dependent variable and the independent variables, and determine their data types (nominal, ordinal, continuous or discrete); c. Discuss the relevance of each independent variable for the prediction of the dependent variable; and d. Develop five (5) store level or product level hypotheses based on the discussion in Step 1(c). For instance, “Stores located in city areas have higher sales because of higher demand for household products”.
The post Produce a data science proposal that discusses the appeared first on My Assignment Online.
