Data Scientist | Featured Fin-tech Company

【ABOUT THE COMPANY】

★ Leading company in the Fintech area
★ The company has been challenging innovative services one after another in the Fintech area, leveraging its technology and financial know-how. Its core services are the AI ​​lending model, a web platform that uses AI, and the management support platform for small and medium-sized businesses, which is deployed in the corporate lending field in the middle of the fintech area. In the midst of developing and developing rapidly.
An industry-focused Fintech venture that is also working on new services that are not bound by the industry's common sense.
After the service launch of the AI ​​loan model, it became a big topic in the financial industry, and conducted KPO with many financial institutions, and the company became a well-known entity.
Behind this service's rapid growth in the Fintech space is the high competitive advantage of technology, big data and financial knowledge. There is no unprecedented use of AI in this area, and in order to surpass the conventional credit model, not only will a large amount of data be required, but also it will be necessary to develop original AI algorithms.
For that purpose, financial knowledge, as well as high AI development skills, are indispensable.
This is an initial advantage and a leading advantage that can only be achieved by the company's focus on this area, and it is now an unrivaled advantage.
The company is also rapidly growing its management support platform, launched three years ago.
As of August 2018, 8,000 SMEs and more than 1,300 specialists (professionals) have introduced them.
Managers can easily consult on the web about daily management issues. Normally, consulting with a specialist (professional worker) costs a considerable amount of time to find the best specialist. Due to the "overwhelming sense of speed", the number of users is rapidly increasing.
Through such advanced business development, the company's presence in the fintech area is further strengthened.
[Business description]
-Development of AI loan screening model for financial institutions Development and operation of next-generation CRM tool.
-Development and operation of Big Advance, a financial institution collaboration platform
-Development and operation of an expert consultation platform

【JOB DESCRIPTION】

With a mission of "Finding the future in corporate value" and a value of "Bringing technology to small and medium-sized businesses", the company is in the business of providing management support to small and medium-sized businesses.
The company was founded in 2007 and was newly listed on the TSE Mothers market in December 2020.
Big Advance, a management support SaaS product launched in 2018, is used by approximately 70,000 member companies through over 80 financial institutions.


Big Advance, a management support platform for SMEs released in April 2018, is marking its 5th anniversary since its release and is a service used by 80 financial institutions and approximately 60,000 SMEs nationwide.
The company plans to promote system improvements to support further expansion of its customer base and the creation of a framework to support the evolution of its business through the platform.
In order to further evolve Big Advance, which is expanding, the company is building a data analysis infrastructure that enables stress-free utilization of the data accumulated in its products and the data of financial institutions with which it has cooperative relationships.
The company is also updating its machine learning model development environment with a view to developing new functions and products on Big Advance, and is looking for more people to join in building the data infrastructure.

The company is looking for new associates who will create the future of the company together!


In this position, you will be in charge of building mathematical models and the modeling part of MLOps, based on the data infrastructure built based on data from inside and outside the company.
You will be responsible for creating an environment that facilitates the utilization of data gathered from various sources and contribute to the acceleration of the company's growth. Specific duties include the following
・Analysis and modeling of data gathered from the company's products and financial institutions
・Operation and management of data pipeline
・Building business dashboards
・Machine learning implementation using Python
・PoC of MLOps and integration into products

＜Skills and experience that you will be able to gain or welcome at the company＞
Experience in a single point of responsibility from company-wide data utilization strategy to building data pipelines and operating and managing business dashboards
Large-scale data analysis and modeling
Knowledge of information security
Experience with data analysis projects
Experience developing and operating machine learning models
Experience building MLOps in the cloud

Technologies/Tools used
■Analytical Environment Construction
AWS
　AWS Glue
　Amazon Athena
　Amazon S3
Python
jupyter lab

■Development Management and Communication
Github
notion
JIRA
Slack

----------------------------------------------------

【 Working time 】

Flextime System

【 Welfare 】

Full Social Insurance
Commuting Allowance
Medical Checkup

【 Holidays 】

2 days a week (Saturdays, Sundays and holidays)
Annual Paid Leave
New Year HolidayBereavement Leave
Summer Holiday
Others

2+ years of working experience in data analysis using Python.
Hands-on experience with recommender systems.
Examples: rule-based, collaborative filtering, content-based filtering, machine learning-based, or hybrid approaches combining these.
Experience with database manipulation and data extraction using SQL.
Understanding of basic statistical techniques such as interval estimation, hypothesis testing, and sample size design.
Ability to leverage data to identify business problems and propose and implement solutions.


Experience in improving search results using ranking algorithms (TF-IDF, BM25, machine learning based, etc.) and natural language processing (NLP).
Experience with feature engineering using user profiles, behavioral log data, text data, etc.
Experience setting goals and improving metrics (MAP, NDCG, MRR, AUC, etc.) used to evaluate recommendations and search algorithms.