Alternative Data and Artificial Intelligence Techniques: Applications in Investment and Risk ManagementКНИГИ » ОС И БД
Название: Alternative Data and Artificial Intelligence Techniques: Applications in Investment and Risk Management Автор: Qingquan Tony Zhang, Beibei Li, Danxia Xie Издательство: Palgrave Macmillan Год: 2022 Страниц: 340 Язык: английский Формат: pdf (true), epub Размер: 28.4 MB
This book introduces a state-of-art approach in evaluating portfolio management and risk based on artificial Intelligence (AI) and alternative data. The book covers a textual analysis of news and social media, information extraction from GPS and IoTs data, and risk predictions based on small transaction data, etc. The book summarizes and introduces the advancement in each area and highlights the Machine Learning (ML) and Deep Learning (DL) techniques utilized to achieve the goals. As a complement, it also illustrates examples on how to leverage the Python package to visualize and analyze the alternative datasets, and will be of interest to academics, researchers, and students of risk evaluation, risk management, data, AI, and financial innovation.
The goal of Machine Learning is to enable computers to learn from experiences in certain tasks. Machine Learning techniques include supervised learning (regression, classification), unsupervised learning (factor analysis, clustering), and new technologies for Deep and Reinforcement Learning which are often used to analyze unstructured data and show promise in identifying data patterns in structured data. We can define Machine Learning as a subset of Data Science, which is often a simple extension of a well-known statistical method that uses statistical models to plot insights and make predictions. The model runs as a background process and automatically provides results based on how it is trained. Data scientists can consistently adjust the training model as needed to maintain considerable effectiveness. In general, the more data that is provided, the more accurate the results are.
To connect to MongoDB from a Python environment, we need the PyMongo Python library. To install PyMongo, type in the command line: “pip install pymongo” To follow the tutorial code, also run “pip install requests”. Requests is a Python library made to create HTTP requests. The following example will use the requests library to retrieve the current price of Bitcoin from coinbase.com. Coinbase.com is developer friendly and offers a free to use API. To navigate through MongoDB databases programmatically with Python, we must first connect to the MongoDB cloud database with the connection string, as we did in MongoDB Compass. After connecting, we then can use brackets after the variable to navigate through databases and collections. PyMongo’s “insert-one” function is then used to insert key-value pairs into the collection. Since data is stored in key-value pairs in MongoDB, programmers conventionally insert Python dictionaries with PyMongo’s insert function.
Скачать Alternative Data and Artificial Intelligence Techniques: Applications in Investment and Risk Management
Навигация
Вход на сайт
Реклама
Alternative Data and Artificial Intelligence Techniques: Applications in Investment and Risk Management 
Название: Alternative Data and Artificial Intelligence Techniques: Applications in Investment and Risk Management
