22576 - Data Analytics - Assessment 2 (1)

Examines Profile Score

check for distribution, to decide whether we use median or mean to replace missing data (TotalVisits)

Conversion rate without duplicate row filter is shown to be 0.383 (38.3%)

Conversion rate after duplicate row filter is shown to be 0.398 (39.8%)

This shows the average mean of people being converted coming from different lead sources (Conversion rate percentage) Conversion varies by acquisition score

Shows the percentage of people converted that did the survey (3185/8316=38.3%)

X education unknown

Lead profile unknown

STATS FOR CLEANED DATASET

Specialization "select" to unknown

City unkown

Standardized all "google" into "Google"

Testing the first Hypothesis of whether time spent on website = higher conversion rate + the others

check for distribution, to decide whether we use median or mean to replace missing data

to verify that an observation either missed all 4 four variables (activity and profile index/score) or not

This compares lead sources to whether it matters when it comes to people being converted

This compares country, however there is a unkown makes a signficant amount towards the resutl

Grouping the average of total time spent on website, total visits, activity score, profile score, page views per visit

This compares whether giving a free copy of masting the interview = customers are more likely to convert