Alphacat Report (November 16–30)

Dear Alphacats!

As part of our efforts to be transparent and have regular communication with our community, we are pleased to share our half-monthly report which includes our progress during this period and our outlook for the future.

Product Development

1. ACAT Store

1) As of the end of November, the ACAT Store listed 15 new third-party applications, increasing the total number of listed applications to 39. These applications are distributed in the following 7 channel categories: Market Forecasting (6 new Apps), Technical Analysis (4 new Apps), Multi Data (9 new Apps), Asset Allocation (2 new Apps), Trading Tools (12 new Apps), Derivatives Market (5 new Apps), and Others (1 new App).

All of the ACAT Store applications are developed by either: Alphacat’s official development team, third party teams integrated with the ACAT platform, or applications fully developed by third parties. In the early days of our platform, most applications were developed via integrated cooperation with the Alphacat Team and third parties. Cooperative development refers to the use of our Alphacat Engine to create and deploy applications. The 39 applications listed in the ACAT Store are ones the Alphacat Team has jointly developed with third parties, and ones that third parties fully developed on their own. We welcome more developers and projects to be part of the ACAT Store and its ecosystem.

For developers, we will support the following:

i) Developers at the conceptual stages of product design.

ii) Developers who already have products listed in the store.

iii) Developers who already have products and are certified by Alphacat.

iv) Developers who are working in cooperation with the Alphacat Team.

In the future, we will provide different services for different types of developers.

2. AI Forecasting Engine

Real-time Forecasting System of Cryptocurrency

Upon the recent results of research conducted by Alphacat, the following conclusions and research paths have been determined:

1) As for the research of financial market data, the usage of the PRNN-LSTM is currently the most suitable for being used in the AI core.

2) Continue to study the pre-processing method of input data information; model optimization techniques; and more targeted algorithm design in the case of multiple price series input.

3) Optimize the design of the target variable to further improve prediction accuracy rates.


As of mid-November, Alphacat’s global community continued its steady growth. The number of our Facebook users continued to rise, from 24,340 to 26,795, an increase of 10.1%. The number of Twitter users increased from 16,709 to 17,212, a growth rate of 3.0%.