We no longer support this browser. Using a supported browser will provide a better experience.

Please update your browser.

Close browser message

As a global leader, we deliver strategic advice and solutions, including capital raising, risk management, and trade finance services to corporations, institutions and governments.

Learn more about our solutions:

  

Serving the world's largest corporate clients and institutional investors, we support the entire investment cycle with market-leading research, analytics, execution and investor services.

Learn more about our solutions:

  

We are a leader in investment management, dedicating to creating a strategic advantage for institutions by connecting clients with J.P. Morgan investment professionals globally.

Learn more about our solutions:

    

Our financial advisors create solutions addressing strategic investment approaches, professional portfolio management and a broad range of wealth management services.

Learn more about our solutions:

    

Leverages cutting-edge technologies and innovative tools to bring clients industry-leading analysis and investment advice.

Learn more:

    

The latest news and announcements.

Learn more:

    

For company information and brand assets for editorial use.

Learn more:

    

The latest news and announcements.

Learn more:

    

In a fast-moving and increasingly complex global economy, our success depends on how faithfully we adhere to our core principles: delivering exceptional client service; acting with integrity and responsibility; and supporting the growth of our employees.

Learn more:

    

J.P. Morgan is a global leader in financial services, offering solutions to the world's most important corporations, governments and institutions in more than 100 countries. As announced in early 2018, JPMorgan Chase will deploy $1.75 billion in philanthropic capital around the world by 2023. We also lead volunteer service activities for employees in local communities by utilizing our many resources, including those that stem from access to capital, economies of scale, global reach and expertise.

Learn more:

    

With over 50,000 technologists across 21 Global Technology Centers, globally, we design, build and deploy technology that enable solutions that are transforming the financial services industry and beyond.

Learn more:

    

Technology Banner

For general inquiries regarding JPMorgan Chase & Co. or other lines of business, please call +1 212 270 6000.

Learn more:

      

For general inquiries regarding JPMorgan Chase & Co. or other lines of business, please call +1 212 270 6000.

Learn more:

      

Synthetic Data

Synthetic Equity Market Data

Synthetic equity market data contains simulated time series of spot and option prices for a given asset. Spot is one-dimensional while options are defined on a high-dimensional grid of relative strikes (e.g. [80%, 90%, 100%, 110%, 120%]) and floating maturities (e.g [20, 40, 60, 120]). The time series is on daily interval.

Simulated data is generated by a machine learning model which is trained on data derived from historical spot and option prices. Historical prices are sourced from Bloomberg via RMDS. For spot, we adjust raw prices by removing dividend, borrow and rates impact. For options, an internal vol fitting process is used to convert raw prices to implied volatilities which are then transformed to discrete local volatilities (DLVs). The transformation is mainly to remove possible static arbitrage from the implied vol surface.     

The machine learning model is then developed using adjusted spot and DLVs data. In the pipeline, preprocessing is first done to compress high-dimensional data to some low-dimensional representations via an auto encoder. Neural network based generative model is trained on the low-dimensional data. The generative model takes inputs from random noise plus some initial state up to time t, and generates next state at t+1. The objective function is to minimize the distance between the generated (fake) and historical (real) conditional distributions. Once the model is trained, it can generate synthetic low-dimensional data, which is then reconstructed to high-dimensional data via the decoder in auto encoder. The generated high-dimensional data contains synthetic spot and DLVs. DLVs are then converted back to option prices.

The shape of the generated data set is (num_paths, num_days, num_variables). For example, if we want to simulate 10000 paths of an asset’s spot and call option prices for the next 252 days. Using the aforementioned option grid, the shape will be (10000, 252, 21) where 21 is for spot and 20 call options. By default we include put options too, so the shape will be (10000, 252, 41)

 

 

References

1.  Deep Hedging: Learning to Simulate Equity Option Markets..
    M Wiese, L Bai, B Wood, H Buehler.

2.  Conditional Sig-Wasserstein GANs for Time Series Generation..
    H Ni, L Szpruch, M Wiese, S Liao, B Xiao.

 


Would you like to know more about AI Research at J.P. Morgan?

For upcoming workshops and updates, visit: