在这个演讲中，我们将使用100％的开源机器学习和人工智能工具，迭代地训练和完善基于真实贷款业绩数据进行贷款违约预测的简单而强大的信贷模型。数据是基于在10年里发放的26亿美元的贷款。 我们将使用诸如numpy、scipy、pandas、statsmodels和scikit-learning之类的Python工具来演示基本用法以及行业最佳实践。 该讲座将涵盖神经网络、自然语言处理、时间序列、处理结构化和非结构化数据以及监督和无监督学习等技术，并会讨论相应的理论基础以及例如可生产化和可扩展性等实际使用中的问题。
Michael Li demonstrates how to iteratively train and refine a simple yet robust credit model for loan-default prediction, based on real-world loan performance data using 100% open source machine learning and artificial intelligence tools. The data is based on US$26 billion in loans issued over 10 years.
Michael uses Python tools like NumPy, SciPy, pandas, statsmodels, and scikit-learn to illustrate basic usage as well as industry best practices and covers techniques including neural networks, natural language processing, time series, processing structured and unstructured data, and supervised and unsupervised learning, discussing both the theoretical underpinnings and the practical issues like productionizability and scalability.
Tianhui Michael Li is the founder and CEO of the Data Incubator. Michael has worked as a data scientist lead at Foursquare, a quant at D.E. Shaw and JPMorgan, and a rocket scientist at NASA. At Foursquare, Michael discovered that his favorite part of the job was teaching and mentoring smart people about data science. He decided to build a startup that lets him focus on what he really loves. He did his PhD at Princeton as a Hertz fellow and read Part III Maths at Cambridge as a Marshall scholar.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org