US Patent 11775522 Surrogate data generation of private data

Features are disclosed for dynamically generating a proxy representation of characteristics associated with a private data set. A computing device can receive a private data set including private or proprietary information. The compute device can determine one or more characteristics that are associated with the private data set. The computing device can further receive a public data library that includes characteristics that are publicly available. The computing device may generate a proxy representation based on the public data library and the proxy representation may include one or more characteristics that represent the private data set. The proxy representation may be provided to one or more entities who are unauthorized to access the private data set. In some embodiments, the private data set may correspond to an exchange traded fund and the characteristics may correspond to risk factors associated with the exchange traded fund.