Professional Documents
Culture Documents
July 2021
CONTEXT, PROBLEM AND OBJECTIVE
• The Policy Maker of the company wants to enable and establish a viable business model to
expand the customer base.
• The way to expand the customer base is to introduce a new offering of packages.
• Marketing cost was quite high because customers were contacted at random without looking
at the available information.
• The company is now planning to launch a new product: Wellness Tourism Package.
• Wellness Tourism is defined as Travel that allows the traveler to maintain, enhance or kick-start a
healthy lifestyle, and support or increase one's sense of well-being.
• For marketing team it’s necessary predict which customer is more likely to purchase the newly
introduced travel package.
USER PROFILE
• 58% of users are males • In age, the range is 18 – 61
years old
• 42% of total are females
• Users mean age is 37 years
old
USER PROFILE
• Close 3,000 users are • The principal designation is
salaried Executive
• Little more than 2,000 users • Few users are AVP and VP
have small business
USER PROFILE
• The users with better • The monthly income for
designation have more AVP and VP users is above
age $30,000USD
LAST CAMPAIGN
• Basic and Deluxe be the The mean Duration of Pitch is
pitches more used by Sales less to 20 minutes. It's
and Marketing Team necessary to see specific
cases for the outliers
INFO CORRELATION
• The best correlation are
Number of Children Visiting
and Number of Person Visiting.
It's normal because why more
children's more persons
10 XGBoost Classifier 0.996475 0.895819 0.981308 0.603636 1.000000 0.794258 0.990566 0.685950
11 Tuned XGBoost Classifier 0.958872 0.860864 0.982866 0.763636 0.830263 0.603448 0.900143 0.674157
3 Tuned Random Forest 1.000000 0.896504 1.000000 0.563636 1.000000 0.833333 1.000000 0.672451
0 Decision Tree 1.000000 0.874572 1.000000 0.658182 1.000000 0.670370 1.000000 0.664220
12 Stacking Classifier 0.980905 0.860864 1.000000 0.709091 0.908062 0.613208 0.951816 0.657673
5 Bagging Classifier Tuned 0.999706 0.891021 0.998442 0.494545 1.000000 0.871795 0.999221 0.631090
4 Bagging Classifier 0.991187 0.880055 0.956386 0.498182 0.996753 0.787356 0.976153 0.610245
2 Random Forest 1.000000 0.886223 1.000000 0.454545 1.000000 0.886525 1.000000 0.600962
7 Tuned AdaBoost Classifier 0.969741 0.866347 0.870717 0.516364 0.965458 0.696078 0.915643 0.592902
9 Tuned Gradient Boosting Classifier 0.908931 0.865661 0.545171 0.385455 0.951087 0.796992 0.693069 0.519608
1 Tuned Decision Tree 0.756463 0.730637 0.682243 0.636364 0.412041 0.373932 0.513783 0.471063
8 Gradient Boosting Classifier 0.879260 0.853324 0.409657 0.320000 0.891525 0.765217 0.561366 0.451282
6 AdaBoost Classifier 0.847826 0.838245 0.306854 0.294545 0.729630 0.658537 0.432018 0.407035
Feature Importances
Conclusions
✓ The model that should be used to help the company is
XGBoost Classifier
• https://danube-region.eu/survey-on-the-impact-of-covid-19-on-
tourism-policies-participate-now/ .Consult 07-15-2021.