MaxDecisions Announces “FinTech Summer” Internship and Scholarship Program[stm_post_details]
MaxDecisions’ Summer Intern Program aims to provide senior undergraduate or graduate students with the opportunity to gain valuable work experience in analytics, marketing and risk management for Fintech industry.
Through project-oriented hands-on assignments and professional development activities, you will obtain a solid understanding of real-world financial and credit risk data, and an overview of risk management lifecycle in the online lending industry.
Now, we offer two project directions: machine learning and web data sights. Both projects will allow you to learn advanced skills, develop cutting edge technologies and show your creativities to transform the lending functions by applying your IT and data science skills.
MaxDecisions Scholarship Awards:
By the potentially helps of your work on the experience development as well as on Fintech industry, MaxDecisions will sponsor Bronze Award ($1000), Silver Award ($1500), and Gold Award ($2000) for the program participants.
Any senior undergraduate or graduate students in quantitative fields such as computer science, economics, statistics, mathematics, business analysis, and finance, etc. are welcome to apply to this program.
The length of the program is 2~3 months at 2019 summer and will be on-site at MaxDecisions Plano Texas office.
Please download the program guidelines below:
- Track / Direction #1: Machine Learning
- Explore advanced machine learning and deep learning algorithms for marketing and credit risk to build predictive models such as propensity model, credit risk model. You will work on:
- Program scripts ingest, clean and process structured and unstructured data
- Apply various EDA (exploratory data analysis) and feature engineering techniques
- Develop predictive models using machine learning and deep learning algorithms
- Tune hyperparameters and validate the models with specific metrics
- Track / Direction #2: Web Data Insights
- Discover new data sources which create the potential for accurate prediction on customers’ likely propensity to apply for a loan, improvements in the quality of accepted applications, reduction in bad rate, or deeper portfolio insights. You will work on:
- Assess public non-traditional and unstructured data using web crawling
- Apply text mining or sentimental analysis to abstract useful information
- Add to machine learning models to evaluate any lift for the model prediction