•  


Private Computation - 文書 - Meta for Developers

Private Computation Solutions

Products Overview

Both Private Lift and Private Attribution are measurement solutions that use encrypted data and are powered by secure multi-party computation (MPC) with select partners such that each participating partner’s data is kept private from the other, and, upon completion of the MPC, each participating partner is only able to view the aggregated output statistics of the computation.

Previously, this type of reporting required at least one party to learn which specific people converted after seeing an ad, considering Meta has the information about who saw an ad and the advertiser has information on who converted. MPC makes it possible for both parties to only learn insights about ads performance, without the need for either party to see the other’s data.

Private Lift is a powerful way to understand the incremental effect of your advertising on Meta’s platform. This is a kind of experiment where we compare groups of people who did and did not have the opportunity to see your advertising to understand its causal impact on specific business objectives, such as brand recognition or conversion.

Private Attribution is a measurement product that determines the user actions that led to the desired outcome between the click of the ad and the conversion. We currently support 1-day click-through attribution.

Begin Setup

If you are ready to begin your Private Computation setup, click on the button below to start on the Amazon Web Services (AWS) website.

Start Private Computation Setup

Documentation Contents

Get Started

Recommendations and guidelines for setting up Private Computation.

Setup Guide

Step-by-step walkthrough of the work needed to set up and run a private measurement study.

Reference

Instructions to support setting up your Private Computation environment and AWS infrastructure.

- "漢字路" 한글한자자동변환 서비스는 교육부 고전문헌국역지원사업의 지원으로 구축되었습니다.
- "漢字路" 한글한자자동변환 서비스는 전통문화연구회 "울산대학교한국어처리연구실 옥철영(IT융합전공)교수팀"에서 개발한 한글한자자동변환기를 바탕하여 지속적으로 공동 연구 개발하고 있는 서비스입니다.
- 현재 고유명사(인명, 지명등)을 비롯한 여러 변환오류가 있으며 이를 해결하고자 많은 연구 개발을 진행하고자 하고 있습니다. 이를 인지하시고 다른 곳에서 인용시 한자 변환 결과를 한번 더 검토하시고 사용해 주시기 바랍니다.
- 변환오류 및 건의,문의사항은 juntong@juntong.or.kr로 메일로 보내주시면 감사하겠습니다. .
Copyright ⓒ 2020 By '전통문화연구회(傳統文化硏究會)' All Rights reserved.
 한국   대만   중국   일본