Introduction

DeepSeek Harness (DSH) uses an “everything is a plugin” architecture. In empirical asset pricing and machine learning research, researchers often need to combine literature review, data evaluation, model training, and report generation. The ZA Research analysis stage plugin is designed to provide this end-to-end automated workflow.

What This Is

This is a model inference plugin maintained by Z Asset, targeting asset pricing and machine learning / deep learning research. It provides full-pipeline support from data processing to model training and report generation.

Core Features

The plugin mainly includes the following capabilities:

  • End-to-end model training and estimation
  • Asset pricing + machine learning / deep learning research
  • Literature review
  • Data processing
  • Model training
  • Report writing
  • PPT creation

Installation and Enablement

Add the plugin using the official installation command:

dsh plugin --profile <your profile> add zresearch-analysis

It can also be installed via npm:

npm install zresearch-analysis

After installation, trigger it on demand in a DSH session. The model will automatically load the corresponding skill based on the task.

Typical Usage

Enter the following instructions in a DSH session to trigger the relevant functionality:

  • Literature review: Ask “Help me do a literature review / find related papers”
  • Data processing: Ask “Help me find data / evaluate a dataset”
  • Model training: Ask “Run regression / train an ML model / predict cross-sectional returns”
  • Report writing: Ask “Write a paper / draft a section”
  • PPT creation: Ask “Create a presentation PPT / Beamer slides / job market talk”

Applicable Scenarios and Notes

This plugin is suitable for users working on empirical asset pricing, factor models, cross-sectional return prediction, GMM/SDF, and related research. The plugin runs with the permissions of the current DSH process. Before installation, review the source code and license.

Resources

  • Plugin directory: https://www.skillhub.cn/plugins/Z-Asset/ZA_analysis
  • Source code: https://github.com/Z-Asset/ZA_analysis