This repository contains analysis using Spark-Scala code for business sales and market basket analysised within a given time period for ecommorce and product based companies
ABSTRACT: Business sales are very important to deterrmine market performance of either a product or producer performance. This can also be illustrative on the market share allocated to these processes. This first analyses show how some fortune 500 companies fared within a given time frame using scala. The findings of the study will help these companies plan strategies on how to increase market performance in a bid to have a dorminant presence in the market.In another study, market basket analysis was conducted for XXX bank. The business questions and solutions can be found below
OBJECTIVE: -This study used big data to determine the market share for a product XXX between Facebook (FB), Google (GOOG) and Microsoft (MSFT).
-A banking institution, ran a marketing campaign to convince potential customers to invest in a bank term deposit scheme. The marketing campaigns were based on phone calls. Often, the same customer was contacted more than once through phone, in order to assess if they would want to subscribe to the bank term deposit or not. Perform the marketing analysis of the data generated by this campaign
Analysis tasks to be conducted:
The data size is huge and the marketing team has asked you to perform the below analysis-
Give marketing success rate (No. of people subscribed / total no. of entries)
• Give marketing failure rate
. Give the maximum, mean, and minimum age of the average targeted customer
. Check the quality of customers by checking average balance, median balance of customers
. Check if age matters in marketing subscription for deposit
. Check if marital status mattered for a subscription to deposit
. Check if age and marital status together mattered for a subscription to deposit scheme
. Do feature engineering for the bank and find the right age effect on the campaign.
METHOD: -The data was uploaded into Atom IDE and Scala and SparkSQL codes where written in Spark environment and processed on Spark-Shell to have a quick look and make apt business conclusions