Supercharge Your Innovation With Domain-Expert AI Agents!

Fund manager recommendation method based on NLP technology and machine learning algorithm

A machine learning and recommendation method technology, applied in the financial field, can solve the problem of not being able to recommend high-quality managers more in line with their ideas and styles for customers, and no way.

Inactive Publication Date: 2022-03-11
融量数据科技(上海)有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method of recommending fund managers after rating them is to compare indicators such as the volatility retracement of the historical performance of the funds managed by the fund managers. It is mainly for the analysis of investment performance. Customers analyze different fund managers, that is, they cannot recommend high-quality managers that are more in line with their philosophy and style

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fund manager recommendation method based on NLP technology and machine learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] Please refer to figure 1 As shown, the present invention provides a method for recommending fund managers based on NLP technology and machine learning algorithms. The recommendation method includes the following steps S1, obtaining a collection of lists with higher comprehensive data of fund manager factor evaluation in the past six months; S2, passing Dialogue with customers, use NLP technology to display various text data of different fund managers, and carry out word meaning labeling and analysis. The text data of fund managers include text materials such as voice texts, road show materials, fund quarterly reports and annual reports; S3, Demonstrate the investment philosophy and investment ability of different fund managers through mathematical modeling, and conduct comparative analysis; S4. According to the customer's own investment requirements and investment styles, select the list of fund managers that meet the customer's requirements from the list collection; S5....

Embodiment 2

[0021] This embodiment is an improvement made on Embodiment 1. For details, please refer to figure 1 , the process of using NLP includes the following steps: text preprocessing, which breaks the text into useful units, then uses techniques such as stemming and lemmatization to convert words into basic forms, which can help reduce noise and simplify analysis, and then use lexical , or study the relationship between words, and then use syntax or analyze how words and sentences are combined, and perform semantic analysis; text representation, describe the words that appear in the document through the bag of words model, and create combined words through the N-gram model , dilute frequently occurring words in documents through TF-IDF, and highlight more unique words with useful information, help better analyze and compare words and context through word embedding; analysis and modeling, using machine learning and deep learning methods perform calculations to produce desired results...

Embodiment 3

[0024] This embodiment is an improvement made on the basis of Embodiment 1. For details, please refer to figure 1 , the fund manager factor evaluation system builds a fund manager factor library from resume information, employment information, performance and other dimensions, including categorical factors and numerical factors, and conducts validity checks on factors on a monthly basis to screen effective factors; the manager factor The evaluation system includes basic information. The basic information dimension includes factors such as educational background and length of service, which are used as auxiliary indicators for evaluating fund manager factors; profitability. The profitability dimension includes factors such as absolute return and excess return; profit Stability, the profit stability dimension includes factors such as performance stability and excess return stability; risk control, the risk control dimension includes factors such as maximum retracement rate and vo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a fund manager recommendation method based on an NLP technology and a machine learning algorithm. The recommendation method comprises the following steps: S1, obtaining a list set with relatively high fund manager factor evaluation comprehensive data in nearly six months; s2, displaying various text data of different fund managers by using an NLP technology through conversation with the customer, and performing word meaning tagging and analysis; s3, displaying investment concepts and investment capabilities of different fund managers through mathematical modeling, and performing comparative analysis; s4, screening a fund manager list meeting the requirements of the customer from the list set according to the investment requirements and investment styles of the customer; s5, predicting future investment performance of the fund manager in the list through modeling and text, and further screening out a proper list; and S6, removing fund managers which do not meet the requirements according to the requirements of the clients, and obtaining a final recommendation list.

Description

technical field [0001] The invention relates to the field of financial technology, in particular to a method for recommending fund managers based on NLP technology and machine learning algorithms. Background technique [0002] In the past ten years, wealth management products have developed rapidly in my country. Among them, public offering fund products with the highest degree of conversion have so far surpassed more than 100 fund companies and more than 6,000 fund products, with an asset scale of more than 8 trillion yuan, and Various types of fund products have been formed, such as stock funds, bond funds, currency funds, FOF funds, etc. More and more customers choose to conduct fund management, and they need to use fund managers to serve customers when purchasing funds. [0003] In order to facilitate users to choose fund managers, major fund companies and related companies recommend fund managers after rating them. The method of recommending fund managers after rating ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/9535G06F40/30G06F40/289G06F40/211G06F40/253G06F40/216G06N20/00G06N3/08G06Q10/04G06Q10/06G06Q40/06
CPCG06F16/9535G06F40/30G06F40/289G06F40/211G06F40/253G06F40/216G06N20/00G06N3/08G06Q10/04G06Q10/06393G06Q10/06398G06Q40/06
Inventor 何滟仇琰敏陈春卉
Owner 融量数据科技(上海)有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com