Advanced implementation of the Nelson-Siegel-Svensson model for yield curve fitting and term structure analysis. This model extends the classic Nelson-Siegel framework with additional flexibility for capturing complex yield curve shapes.
def nelson_siegel_svensson(maturity, beta0, beta1, beta2, beta3, tau1, tau2):
"""Nelson-Siegel-Svensson yield curve model"""
term1 = beta0
term2 = beta1 * ((1 - np.exp(-maturity/tau1)) / (maturity/tau1))
term3 = beta2 * (((1 - np.exp(-maturity/tau1)) / (maturity/tau1)) - np.exp(-maturity/tau1))
term4 = beta3 * (((1 - np.exp(-maturity/tau2)) / (maturity/tau2)) - np.exp(-maturity/tau2))
return term1 + term2 + term3 + term4
Built comprehensive yield curve analytics including parameter estimation via non-linear optimization, forward rate calculations, and duration risk metrics with improved fitting accuracy.
Python
NumPy
SciPy
Fixed Income
Quantitative Finance
Advanced statistical modeling system combining spline interpolation with Monte Carlo simulation for budget forecasting and risk management. Built comprehensive analytical framework for uncertainty quantification in annual spending patterns.
Methodology
1. Spline interpolation for smooth spending curves
2. Monte Carlo simulation (10,000+ iterations)
3. Probabilistic risk assessment & confidence intervals
4. Interactive dashboard development for stakeholders
import numpy as np
from scipy.interpolate import UnivariateSpline
import matplotlib.pyplot as plt
def monte_carlo_budget_simulation(historical_data, n_simulations=10000):
"""Monte Carlo simulation for budget forecasting"""
# Fit spline to historical spending patterns
spline = UnivariateSpline(months, spending_data, s=0.1)
# Generate random scenarios
scenarios = []
for _ in range(n_simulations):
noise = np.random.normal(0, volatility, len(months))
scenario = spline(future_months) + noise
scenarios.append(scenario)
return np.array(scenarios)
Developed interactive dashboards enabling real-time budget analysis with probabilistic forecasts. Implementation includes risk metrics calculation, scenario analysis, and automated reporting tools used by finance teams for strategic planning decisions.
Python
NumPy
SciPy
Matplotlib
Monte Carlo
Spline Interpolation
Risk Management
Data Analytics
Full-stack web application serving 14,000 students and 160 clubs at Brooklyn College. Built comprehensive club management system with real-time data synchronization and automated administrative workflows.
Frontend (HTML/CSS/JS)
↓
API Layer (Google Apps Script)
↓
Database (Google Sheets + Cloud Storage)
↓
Admin Dashboard (Automated Reports & Audit Tools)
Implemented backend database management using Google Apps Script with automated data validation, audit trails, and real-time synchronization. Created administrative tools for managing club registrations, event tracking, and compliance reporting.
// Google Apps Script - Database sync function
function syncClubData() {
const sheet = SpreadsheetApp.getActiveSheet();
const data = sheet.getDataRange().getValues();
// Data validation and audit logging
data.forEach((row, index) => {
if (validateClubRecord(row)) {
updateClubStatus(row);
logAuditTrail(row, 'UPDATED');
}
});
}
HTML/CSS/JS
Google Apps Script
Database Design
API Development
System Architecture
