Name: Paola A Carvajal Almeida, CIPM
Type: User
Company: RSI Inc.
Bio: Passionate about quantitative finance. 10+ years of experience in the Investment Mgmt Industry, including asset management, research, and software development
Location: San Francisco, California
Blog: linkedin.com/in/paolacarvajal
Paola A Carvajal Almeida, CIPM's Projects
Financial tool that construct an optimized and diversified portfolio for a user given her level of risk and her current portfolio.
The present project uses Python and Pandas to analyzes opportunities for arbitrage in Bitcoin during the big crush of Q1 2018, when the bitcoin price fell by 65% in a month period. The analysis compares buying/selling on two major exchanges: Bitstamp and Coinbase.
This code build a blockchain-based ledger system with a user-friendly web interface. This ledger allows partner banks to conduct financial transactions (that is, to transfer money between senders and receivers) and to verify the integrity of the data in the ledger.
Uses K-Means unsupervised machine learning algorithm and Principal Component Analysis to cluster cryptocurrencies based on performance in selected periods.
Python code that enables a user, such a human resources department of a company, to send cryptocurrency payments to its professionals
Build a financial database and web application by using SQL, Python, and the Voila library to analyze an ETF performance.
Preliminary deep learning model to predict transactions fraud.
Source code for James Lee's Docker course
This project uses Json data from Alpaca APIs and Montecarlo Simulations for portfolio valuation and projections for financial planning..
Time series analysis showing trend, seasonality, and periodicity decomposition; and forecasting using Facebook Prophet. The analysis makes extensive use of indexing data tools and of the Pandas and Datetime libraries.
Use of visualizations with PyViz and Plotly Express to show results on geographical real estate data analysis.
Several exercises about specific topics in Python made in Jupyter Lab, some interesting work from other developers, and in general, useful material for Python.
COntains sources of data that use a lot of space
Phyton modular interactive application to determine the set of banks for which a user would qualify, based on her credit score and other financial information that will be asked through the terminal.
Apply machine learning SVM and AdaBoost algorithms to an algorithmic trading strategy.
All the code examples I use in https://www.youtube.com/watch?v=0kzjD6jvfnk money representation video
Config files for my GitHub profile.
Python scripts with procedures for a wide variety of financial applications
Quantitative analysis to select one fund among several, for inclusion in a suite of products for retirement portfolios, using key metrics, visualizations, and diversification considerations.
This project constructs a smart contract to automate an institutions’ financial process of hosting joint savings accounts.
Risk attribution report for portfolio management, using MatLab and Excel
Uses Logistic Regression and various machine learning techniques to train and evaluate models with imbalanced classes applied to identify the creditworthiness of borrowers.
TensorFlow and Keras are used for the construction and evaluation of Deep Learning models to predict success of companies that receive funding from a venture capital fund.
Machine learning model to predict the sign of the VIX Index for the next day.
An algorithmic trading strategy incursion using Adaboost machine learning classifier, to create the first volatility security suitable for long term investors.
Project description tbd...
Yahoo! Finance market data downloader (+faster Pandas Datareader)