Customer Analysis|Portfolio Analysis|Asset Allocation|Risk Allocation|Economic Forecast|Sales Forecast

Fifteen easy-to-use tools use the knowledge of personality psychology, portfolio theory, macroeconomics, customer relationship management, mathematical statistics and machine learning, allowing you to easily share ideas and improve work efficiency.

Learn more

Career 3A

Sketch the core of your career.

Career 3A can quickly outline your behavior style, career drive and personal skills. Based on your assessment results, list the most suitable occupations to help you think about the direction of career choices. You can invite friends to form a team and query the assessment results of the team by entering the same team name, which can help you better establish relationships with colleagues who have different priorities and preferences.

Download on the App Store.

Behavior Styles

This assessment can quickly determine your behavior styles.

Career Drivers

This assessment will help you understand what is driving your career.

Personal Skills

This assessment will help you decide which personal skills are your favorite to use at work.

Cluster 2A


Cluster Analysis Tools.

Clustering is an unsupervised machine learning technique that groups similar objects into the same cluster. Cluster 2A combines the two most popular clustering algorithms, K-means and DBSCAN, to help you discover interesting patterns in the data. For example, it can help you find different customer groups based on customer consumption behavior.

K-means Model

The K-means algorithm requires the number of clusters to be specified. Its main goal is to find representative data points in a large amount of high-dimensional data, which are called centroids, and then assign the nearest centroid to each data point based on these centroids. It can be well extended to a large number of samples and has been widely used in many different fields. Cluster 2A uses K-means++ to select the initial cluster center to improve the convergence speed.


Unlike K-means, DBSCAN does not need to specify the number of clusters to be generated. The DBSCAN algorithm processes data points based on density, mainly dividing sufficiently dense points in the feature space into the same cluster, and can identify outliers that do not belong to any cluster, which is very suitable for detecting outliers.

Download on the App Store.

Feature Data
You can create a database based on the customer's purchase behavior (RFM).
K-means Model
This algorithm divides all points in the sample space into K similarity groups.
This algorithm is very effective in detecting outliers and dealing with noise.