Create Powerful Customer Segments for Marketing | Data Analysis for Beginners #4
ฝัง
- เผยแพร่เมื่อ 9 ธ.ค. 2022
- Learn how to create a great marketing segmentation analysis and presentation to impress your managers with a RFM Model (Recency, Frequency and Monetary).
You will be to identify your most value customer and dormant customers to further customize your marketing campaigns for maximum effect.
Check me out on Linkedin
/ gaelimholland
Video Contents:
0:14 Problem Statement
1:17 Dataset Exploration
2:46 Pivot Tables and Create Main Variable
5:57 Calcuating Recency
9:51 Using Percent Rank
14:49 Calculating RFM Scores
16:48 Creating Segments
20:00 Segment Analysis and Visualization
21:30 Presentation
You can find the dataset here for analysis:
www.kaggle.com/datasets/carri...
#excel
#marketing
#dataanalysis
#segmentation
#clustering
#rfm
Business + Technical, very Well done!!!
Glad that you like it!
Thank you so much sir I have been looking for this analysis from so long but none of the videos on you tube has given me that kind of insight..❤
This is an excellent comment. Glad you liked it
This could by far be the most useful data tutorial I have watched and very applicable to all sorts of data sets if you think about your own customer base and what could be considered their recency, frequency and monetization measures. 🙏
Hey!!! Love your comment. I am glad you found this tutorial very useful.
Great video! Thank you!
Glad you liked it. Share it will anyone you think it will help.
Top content as usual.
Glad you think so!
some dates are not recognized at dates and i get the value 0 for max invoice for all of them
Thank you💯🔥❤️🇿🇦 can I please also ask for this done in python, would help me in my data analysis journey
you are so great person thank you
So nice of you
Throughout whole youtube I have seen most of the channels used similiar dataset . Can you pls do the same project using different dataset.
very good
really goo insight and very clever
Thank you
Hello, this video is really great and i want to thank you for doing it. A real time and effort saver.
I do have a question that makes me feel stupid, but in my dataset i have 639 customers, and i have done exactly like you do.
I dont understand why the percentrank make it so my scoring places like this: 30-27=10, 26-24=9, 23-21=8, 20-19=7, 18-17=6, 16-14=5, 13=4, 12-10=3, 9-8=2, 7-5=1, 4-1=0. Why is for example 14 alone with the score of 4? Is this correct?
Should it not be equal intervalls between the Scores 30-1, and the customers score individual score then places them in a interval that has equal amount of numbers in it?
I hope this makes sense, again great video, liked!
Thanks
I used this method on our sales dataset but there's always blanks ("-") appearing in monetary and RFM score even though the scores for monetary, frequency, recency are complete. Could you tell me why?
How did you get the $7200 you concluded in the end and 10days average?
Hello I got another question. How do you get the frequency? I downloaded the data set that is linked in the video but it doesn't have the frequency column. How do I get the frequency?
This is definitely covered in the video. Watch it from the beginning. You missed it
@@absentdata Yeah I actually missed it . Anyway Thank you for the reply.
can some one help me while convering date to max in pivote im getting 0 insted of value and then changing to date give me date in 1900
Try these steps: first convert date format in pivot table it will come 1900 but don't worry, go to field setting select max then it will be ok. it worked for me.
Where can I get the data that you used in the video?
It's in the description
@@absentdata One more question, so I have a problem getting the recency. let say I have a 12/01/2010 to 12/31/2012 using datedif, the resulting is always the #value! error. What should I do?
Great content but please provide the dataset
It's in the description.
joe rogan now has a Marketer career
Lol!
I just want to confirm , that RECENTCY is worse ---> if there are many ?
If I understand your question, the answer is yes, its worse.