SimCode: AI Financial Analyst

Simcode is a global economic simulator research and development company. Our mission is to contribute to humanity by clarifying the causal relationships within the world economy.

Our goal is to analyze the complex mechanisms underlying the world's economic activities automatically in order to provide new value for future economic development.

We have been conducting research to automatically discover and learn causal relationships between various economic data.

We call the series of analytical models we have discovered in this research the Causal Intelligence Model.

We are currently developing a solution using a Causal Intelligence Model to address the challenge investors face when they don't know whom to consult about U.S. stock investments.

We hope to continue contributing to global economic analysis through the development of the Causal Intelligence Model.

OUR SERVICE

We are engaged in the research and development of an AI/LLM-based financial analyst utilizing an economic causal inference model known as the Causal Intelligence Model (CIM).

This AI financial analyst learns the relationship between economic events and stock prices, much like a human analyst, and provides real-time answers to investment-related questions. It specifically addresses the challenge faced by many novice investors who often don’t know whom to consult when investing in U.S. stocks.

For example, it can answer a wide range of questions, from beginner-level inquiries such as "What stocks do you recommend?" to professional-level questions like "Which economic indicators influence Apple’s stock price?"

We are always eager to hear from anyone interested in our product. Feel free to contact us anytime.

Our offices

Santa Clara, California

Causal Intelligence Model

The Causal Intelligence Model (CIM) is an advanced technology designed to simplify complex economic causal inference simulations. Like a human financial analyst, CIM learns the causal relationships between economic events and stock prices, performing inference with remarkable precision.

With CIM, we generate long-term economic forecasts and conduct medium- to long-term stock price predictions and simulations. For example, CIM has achieved an impressive average accuracy of 88.7% in stock price forecasts for the top 100 U.S. companies by market capitalization over the past year. Additionally, CIM allows users to view the historical forecast accuracy for each individual stock, enabling them to see which stocks the model forecasts with high accuracy.

CIM's true value lies not only in its forecast accuracy but also in its causal inference capabilities. By identifying which economic events influence specific stock prices, CIM provides highly reliable explanations that build confidence in its forecasts, allowing users to make more informed investment decisions and mitigate risks.

The output of CIM goes beyond stock prices. In the future, we expect CIM to support real-time economic simulations with a wide range of outputs by incorporating additional parameters.

This innovative technology has the potential to revolutionize economic analysis, offering rapid insights into the causal and correlational relationships within economic data through advanced time-series analysis.

We are experts in economic data analysis and machine learning who have come together to accomplish something ambitious.

"Simcode" describes the unraveling of complicated modern economic mechanisms using our Causal Intelligence Model with economic causal relationship learning technology as its core (just like solving the Da Vinci Code!)

Simcode founders Hiro Nakagawa and Kaira Sekiguchi, Ph.D., originally created innovative, cutting-edge technology to study investment trends.

We remain passionate about making it easy for our customers to get the most value from our global economic simulations.

And the use of this technology is not limited to stock price forecast simulators. We will continue to analyze Code related to economic data using this technology as a base to create new value for future economic development.

During our research, we discovered causal relationships between various types of economic data using automated techniques and wanted to apply this economic causal relationship model to useful business applications – so we founded Simcode.