CARI TAU POLA PEMBELI AMAZON DENGAN SEGMENTASI PELANGGAN | Luthfi | Student Project| Algoritma 2024

Summary

In this presentation, the speaker discusses their final project on customer segmentation for an online shopping platform, using data from Amazon India. They explain the importance of segmenting customers based on attributes and how this can help businesses maximize revenue. Through clustering methods, three customer segments are identified: 'simplicity shoppers', 'driver shoppers', and 'seasonal shoppers', each with distinct buying behaviors. The analysis reveals patterns in purchasing times, age groups, and product preferences, with a focus on how these insights can be applied to online shopping in Indonesia. The speaker hopes the findings will be useful for businesses targeting similar consumer segments.

Takeaways

• 😀 The speaker introduces their final project focused on customer segmentation and data analysis of Amazon shopping behavior.
• 😀 The data used in the project originates from India but is expected to be applicable to the Indonesian market.
• 😀 Customer segmentation is defined as dividing individuals into groups based on shared attributes to improve business targeting.
• 😀 The speaker uses One-Hot Encoding to convert categorical data into numerical format for analysis.
• 😀 Clustering is performed using WSS (Within-Cluster Sum of Squares) to create meaningful customer segments.
• 😀 Three customer segments are identified: Simplicity Shopper (average age 23), Diver Shopper (average age 34), and Seasonal Shopper (average age 48).
• 😀 Simplicity Shoppers are primarily young females who prefer fashion and clothing items.
• 😀 Diver Shoppers tend to have varied product preferences and prefer personalized recommendations.
• 😀 Seasonal Shoppers prioritize product reviews and use filters when searching for products.
• 😀 The analysis reveals key shopping patterns, such as customers purchasing most often around 5 PM and on Wednesdays.
• 😀 The age group of 23-year-olds is the largest customer base, with a noticeable preference among females in this group.
• 😀 The speaker provides a profiling summary, showing how different segments behave in terms of purchase frequency, satisfaction, and product category interests.
• 😀 The cleaned dataset contains 33 columns, providing detailed insights into customer demographics and purchase behavior across various categories.
• 😀 The speaker concludes that the insights from the data can be applied to the Indonesian market due to similarities in customer behavior and the potential for mutual benefit between online shops and customers.

Q & A

What is the primary focus of the presenter’s final project?

The primary focus of the presenter’s final project is customer segmentation in online shopping, specifically using data from Amazon in India, and analyzing it to apply similar insights to Indonesia.

What is customer segmentation and why is it important for businesses?

Customer segmentation is the process of grouping individuals based on shared characteristics or attributes. It helps businesses understand their customers better, allowing them to tailor their offerings and maximize revenue by identifying customer needs and buying behaviors.

What data was used for the customer segmentation analysis?

The data used for the analysis comes from Amazon in India. Although the data is from India, the presenter believes the insights are transferrable to the Indonesian market.

How was the data processed for segmentation?

The data was processed using a one-hot encoding technique to convert categorical data into numerical data. This was followed by clustering using the WSS (Within-Cluster Sum of Squares) method to determine the optimal number of segments.

What were the results of the clustering analysis?

The clustering analysis resulted in three customer segments: Simplistic Shoppers (younger, primarily female, interested in fashion), Driver Shoppers (older, more diverse product interests, prefer personalized recommendations), and Season Shoppers (older, prioritize product reviews and use filters).

What is the significance of the clustering result of three segments?

The significance of the three segments is that each represents a distinct customer profile with different purchasing behaviors, which helps businesses target and serve these groups effectively with tailored marketing strategies.

What were the key findings regarding customer purchasing behavior?

The key findings were that the majority of Amazon customers make purchases around 5 PM, with Wednesday being the most common day for purchases. The average age of customers is 23, and there is a significant difference in the gender distribution, with females being the majority among younger customers.

What insights were gained from the age and gender distribution data?

The data revealed that the majority of Amazon users are 23 years old, with significant gender differences. Younger customers tend to be female, while other age groups, such as 31 years, also show notable purchasing trends.

How can businesses apply the customer segmentation analysis to their own practices?

Businesses can apply the customer segmentation analysis by using similar clustering techniques to categorize their customers, tailor marketing strategies, optimize product recommendations, and improve customer satisfaction by understanding their preferences and purchasing patterns.

What does the presenter hope the analysis can contribute to online shopping businesses in Indonesia?

The presenter hopes the analysis can help businesses in Indonesia understand customer segmentation better, allowing them to use similar strategies to improve their services, increase sales, and create a more efficient shopping experience for customers.