Financial analysis
I study how businesses allocate capital, report performance, and create or absorb risk.
- Corporate finance
- Valuation
- Financial statements
- SEC filings
- Capital budgeting
- Risk and return
Finance × Data × Technology
Turning financial complexity into usable intelligence.
I build software and quantitative systems for financial markets. MS Finance candidate at W. P. Carey, BS Computer Science from the Ira A. Fulton Schools of Engineering at ASU.
Chaitanya SinghFinance + Computer Science
Arizona
MarketsRiskDataSystemsResearch
The practice
What I work on
Financial reasoning, quantitative methods, and product engineering brought into one working system.
Quantitative systems
I build models and pipelines that turn market behavior into measurable, testable signals.
- Volatility modeling
- Monte Carlo simulation
- Regime detection
- Risk calculations
- Market data pipelines
Product engineering
I build the infrastructure and interfaces that move analysis from a notebook into useful decisions.
- Backend architecture
- APIs
- Data infrastructure
- Applied machine learning
- Clear interfaces
Current focus
Now
September 2026
01
I am deepening my finance and accounting coursework at W. P. Carey.
02
I am building quantitative and machine-learning systems for market analysis.
03
I am making financial analysis understandable to people without a finance background.
Finance in practice
Selected work.
Portfolio construction, credit decisions, financial research, and the systems that connect them.
Portfolio construction
01Financial systems
PortfolioPilot
Quant portfolio optimizer and backtesting lab with a Next.js analytics dashboard and live market data integrations.
Finance & coverage
02Financial systems
Synaxis (MoneyMatters)
24-hour hackathon platform that combines personal finance management with AI-powered insurance policy analysis, coverage-gap detection, and scenario simulation.
Explainable credit risk
03Financial systems
CreditLens
Demo credit default risk scoring platform with explainability, fairness diagnostics, and an underwriter dashboard.
Transaction intelligence
04Financial systems
FraudPulse
Real-time fraud detection platform with a Next.js analyst dashboard, API/worker pipeline, and ML scoring service.
Market research agents
05Financial systems
HedgeFundAIAgent
Agent workflow exploring hedge-fund style research, data ingestion, and signal summaries.
Time-series research
06Financial systems
StockMarketPredictions
Stock prediction and analysis toolkit covering EDA, RSI calculation, time-series visualizations, and ML models for classification and regression.
Analysis in progress
Research notes
Jul 22, 2026
Completing Apex Arena: Shipping the Live Data and Replay Stack
Apex Arena is complete: a production Formula racing experience with resilient data handling, replayable race rooms, and a verified delivery path.
Jul 8, 2026
Fine-Tuning Is a Lifecycle, Not a Training Run
How to operate an adapted model with evaluation gates, versioning, monitoring, and a disciplined rollback path.
Jun 17, 2026
Choosing Full Fine-Tuning, Adapters, or LoRA
A decision guide for selecting an adaptation strategy based on task shift, cost, inference constraints, and operational needs.
Operating principles
How I build.
Technology should handle the complexity. The user should receive clarity.
01
Curiosity
Start between disciplines and follow the question wherever the evidence leads.
02
Clarity
Make complexity legible without removing the nuance that matters.
03
Trust
Show sources, limits, assumptions, and uncertainty.
04
Execution
Build beyond the first demo and design for the work of operating it.