Resource center-Ruihe Data Technology Holdings Limited-

Index
About Us+
- About Us +
- Corporate History +
Products+
- Intelligent marketing +
- Artificial Intelligence +
- Big data +
Solution+
- Smart Marketing +
- Artificial Intelligence +
- Big Data Platform +
Cases+
AI Lab+
- The AI Lab +
- The training system for leading analysts +
Investor+
- Corporate Governance +
- Information Disclosure +
- Contact Us +
Contact+
- Join Us +
- Contact Us +
Trial+

Live Broadcast Notice

All Live

In the era of wealth management 2.0, how can financial institutions break through digital marketing?

Speaker：joe
Watch Replay
Customer group division & business practice of retail bank customer management

Speaker：joe
Watch Replay
An interpretable solution for anomaly detection in the financial industry & its multi-scenario application

Speaker：Zhang Zimian，So Xinda Holdings
Watch Replay
Suoxinda Lingmo Panoramic Regulatory Compliance Platform Product Online Conference

Speaker：Suoxinda Holdings
Watch Replay
Financial industry data asset management implementation path & innovative application

Speaker：Wei Qiang，So Xinda Holdings
Watch Replay
Financial sector new generation customer label system floor application & design ideas

Speaker：Zhang Weining Social Holding T
Watch Replay

Download

Latest Research

Networks in social networks represent learning techniques

View Details

In the second half of the bank transformation, the MAU (monthly living) ecological action and thinking were attacked

Create the MAU ecosystem

Since 2013, the huge impact of Internet finance on banks has made people feel a great threat. The threat mainly comes from the fact that it is a new business model.

Download Report
Networks in social networks represent learning techniques

The social network

Traditional network representation generally uses high-dimensional sparse vectors. However, the high-dimensional sparse representation has also become a limitation when people use statistical learning methods, because high-dimensional vectors will cost more running time and computing space. With the development of presentation learning technology, researchers have turned to explore the low-dimensional and dense vector representation of nodes in the network, which has become a challenge to effectively integrate network structure and external information of nodes to form a more differentiated network representation

Download Report
(ii) Interpretable neural network based on network structure constraints

SOSxNN model

本章首先通过模拟实验来测试 SOSxNN 模型的性能。结果显示，SOSxNN 模型能够将复杂函数分解成几个较为简单的成分，并取得与经典黑盒算法相近的预测精度。然后，我们使用美国 P2P借贷公司 Lending Club 数据集来展示 SOSxNN模型在金融领域的应用。

Download Report

See More >

Experience it now and start the journey of digital transformation !

DEMO APPLY