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




Personality
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.

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.
Career 3A
Core of Career
Career 3A
Job Matching
Career 3A
Team Analysis
Cluster 2A
Clustering
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.
DBSCAN Model
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.
Feature Data
K-means Model
DBSCAN Model
Cluster 2A
K-means Model
Cluster 2A
DBSCAN Model
Allocation
Allocation 3M
Resource Allocation Calculator.
Allocation 3M combines three mathematical statistical models to help you analyze resource allocation issues in life, such as time allocation, manpower allocation, commodity allocation, etc. These models provide three allocation strategies based on the past data of allocation targets: high expected growth rate, low volatility and volatility parity. When you are facing resource allocation decisions, these strategies provide you with reference information on the data side.
Mean Variance Model
The mean variance model calculates the expected growth rate and volatility based on the past data of the allocation target. Use Monte Carlo method to find the allocation ratio with the highest expected growth rate under a given volatility or the allocation ratio with the lowest volatility under a given expected growth rate.
Black–Litterman Model
The Black-Litterman model combines the mean variance model, Bayesian estimation method, and users’ views on the expected growth rate to calculate the resource allocation ratio. If you have your own views on the future expected growth rate, you can use the Black-Litterman model to calculate the allocation ratio with the highest expected growth rate under a given volatility or the allocation ratio with the lowest volatility under a given expected growth rate.
Risk Parity Model
Unlike the mean variance model and the Black-Litterman model, which are designed to optimize expected growth rates, the risk parity model is designed to optimize volatility. The risk parity model uses Newton’s method to calculate an approximate resource allocation ratio so that the volatility contribution of each data to the data combination is consistent.

Mean Variance Model
Seek the resource allocation ratio with the best expected growth rate.

Black–Litterman Model
Add in the view of expected growth rate to calculate the resource allocation ratio.

Risk Parity Model
Seek the resource allocation ratio with the same volatility contribution of each data.
Allocation 3M
Mean Variance Model
Allocation 3M
Black–Litterman Model
Allocation 3M
Risk Parity Model
Forecast
Macro 3M
Macroeconomic Analysis Tools.
Macro 3M uses three machine learning models to analyze the market response after the release of monthly economic indicators in the US, find out rules, and establish generalized models. You can use these models to input monthly indicator data to map the market performance next month and help you analyze the impact of economic indicators on the market.
The dataset used by Macro 3M contains 22 US economic indicators from 1962 to 2020. After analyzing through statistical tools, six of these indicators are highly correlated with the US market. The six indicators are Nonfarm Payrolls (NFP), Commercial and Industrial Loans (C&I Loans), Personal Income (PI), M2 Money Stock (M2), Industrial Production Index (IPI) and Producer Price Index (PPI).
Macro 3M uses three deep learning models in machine learning: Multilayer Perceptron Model, Recurrent Neural Network Model and Long Short-Term Memory Network Model. The evaluation metrics of these models is to minimize the mean absolute error (MAE) between the mapped value and the target value.
In machine learning, our goal is to obtain a generalizable model that performs well on data that has never been seen before. Under this goal, in the models we track, the performance of deep learning models is better than traditional machine learning models.

MLP
Multilayer Perceptron Model
RNN
Recurrent Neural Network Model
LSTM
Long Short-Term Memory ModelMacro 3M
MLP Model
Macro 3M
RNN Model
Macro 3M
LSTM Model
CRM
Sales TSK
Analyze your sales core.
Sales TSK is a sales tracking tool composed of time matrix, sales stages and key indicators, which can guide you to focus your time and energy on the sales process. Based on your past sales data and current sales targets, calculate key indicators and forecast sales results.
Time Matrix
The time matrix is a simple and effective tool that can prioritize your sales activities according to the urgency and importance of each activity. The time matrix can help you quickly determine which activities should be focused on and which activities should be ignored, thus making time for important activities.
Sales Stages
Divide your sales process into several clear stages, such as contact made, needs defined, proposal made, closed/won, etc. Clear sales stages visualize the sales process, and when you control each stage, you will control the final result.
Key Indicators
Calculate key sales indicators based on your past sales data and current sales targets, forecast your sales results and the number of leads you need. Key indicators include deal size, sales cycle and win rate. You can look for bigger deals, shorter sales cycles, and higher winning rates to improve sales performance.

Time Matrix
Prioritize your sales activities according to the urgency and importance of each activity.

Sales Stages
Guide you to focus on the sales process. When you control the process, you control the final result.

Key Indicators
Analyze key indicators such as deal size, sales cycle and win rate, and forecast sales results.