What We Do
Research-led strategies, algorithmic execution and explicit risk limits for institutional portfolios.
Our Philosophy
We turn academic research into testable investment rules, validated through backtests and out-of-sample analysis.
Patterns We Exploit
Behavioral Finance
We exploit systematic biases in human decision-making. Investors consistently overreact to news, chase past performance, and exhibit loss aversion - creating predictable patterns we can capitalize on.
- Momentum and mean-reversion effects
- Overconfidence and herding behavior
- Disposition effect exploitation
Read more →
Distribution Analysis
Financial returns exhibit negative skewness - meaning large losses occur more frequently than traditional models predict. We design strategies that account for and profit from this asymmetry.
- Tail risk management
- Volatility arbitrage
- Skewness premium harvesting
Read more →
Factor Investing
We systematically harvest risk premia across multiple factors that have been proven to deliver excess returns over time, including value, momentum, quality, and low volatility.
- Multi-factor portfolio construction
- Dynamic factor timing
- Cross-asset factor exposure
Read more →
Understanding Negative Skewness
Returns are not normally distributed. Our risk framework accounts for tail losses through hedging, volatility targets and explicit risk limits.
Risk Management Framework
Our risk models go beyond Gaussian assumptions - we quantify true tail risk using empirical distributions and daily 99%-Value-at-Risk thresholds.
Read more →
Normal vs. Skewed Fat-Tailed Distribution
Real asset returns exhibit both fat tails and negative skewness - many small gains, rare but severe losses
- Normal Distribution (Gaussian)
- Skewed Fat-Tailed Distribution
Fat tails + negative skewness. The empirical distribution of equity returns shows a longer left tail - reflecting the reality that markets produce frequent small gains but rare, severe losses. At the 99% confidence level, Gaussian models predict daily losses ranging from −2.19% to −3.23%, while empirical historical simulation reveals actual losses of −3.38% to −5.32% - underestimating downside tail risk by 44–65%.
Empirical Analysis - Major Indices
Daily 99%-VaR and skewness metrics vs. Gaussian predictions
Value-at-Risk (VaR) estimates the maximum expected loss over a given time horizon at a specified confidence level - e.g. a 99%-VaR of −2.5% means that on 99 out of 100 days, the portfolio loss should not exceed 2.5%.
Normal
-2.35%
Empirical
-3.38%
Gap
44%
-0.55
Normal
-3.23%
Empirical
-5.10%
Gap
58%
-0.62
Normal
-2.93%
Empirical
-4.47%
Gap
53%
-0.74
Normal
-3.08%
Empirical
-4.78%
Gap
55%
-0.68
Normal
-2.19%
Empirical
-3.41%
Gap
56%
-0.65
Normal
-3.22%
Empirical
-5.32%
Gap
65%
-0.72
Empirical VaR based on historical simulation of daily returns (1990–2024). Normal VaR = −2.326 × σ_daily where σ_daily = annualised vol ÷ √252. Annualised vols: S&P 500 ~16%, NASDAQ 100 ~22%, Euro Stoxx 50 ~20%, DAX 40 ~21%, MSCI World ~15%, MSCI Emerging Markets ~22%. MSCI World and MSCI Emerging Markets volatility and VaR estimates: MSCI Factor Investing Research (2023), Dimson, Marsh & Staunton (2024 Global Investment Returns Yearbook). Skewness estimates: Cont (2001), Bali et al. (2008). Sources: Bloomberg, MSCI, Stoxx Ltd., Deutsche Börse Group. Past performance is not indicative of future results.
Deep Investment in Technology
We equip our strategies with the latest technology, advanced tools and extensive resources with the goal of making them faster, more resilient and more effective.
Cloud-Native Infrastructure
Scalable, resilient systems built on modern cloud architecture for maximum uptime and flexibility.
Read more →
Big Data Processing
Real-time ingestion and analysis of terabytes of market data, news, and alternative data sources.
Read more →
Modern Development
Python, R, and C++ for quantitative modeling with strict version control and automated testing.
Read more →
Enterprise Security
Bank-grade security protocols protecting algorithms, data, and client information.
Read more →
From Data to Alpha
Our systematic pipeline transforms raw market data into actionable trading signals through a rigorous, multi-stage process.
01 / 05 · DATA INGESTION
Raw Data
Daily prices, volumes and volatility of the traded markets, plus interest rates and macro releases, are collected from several independent sources.
- Sources cross-checked against each other
- Stored unchanged with timestamps
- Gaps and outliers flagged on arrival
e.g. prices · volumes · volatility · rates · macro
Hover or click a stage to explore it. Use the arrow keys to step through.
Daily prices, volumes and volatility of the traded markets, plus interest rates and macro releases, are collected from several independent sources.
- Sources cross-checked against each other
- Stored unchanged with timestamps
- Gaps and outliers flagged on arrival
e.g. prices · volumes · volatility · rates · macro
The Algorithmic Advantage
No Emotional Bias
Algorithms don't panic during market crashes or get euphoric during bubbles. Our systematic approach removes the emotional decision-making that costs investors billions annually.
Read more →
Consistent Execution
Every trade is executed according to predefined rules, ensuring perfect consistency across thousands of decisions. No style drift, no key-person risk.
Read more →
Scalable Alpha
Our strategies can be scaled across markets and asset classes without losing their edge. The same rigorous process applies whether managing millions or billions.
Read more →
Our Research Process
Hypothesis
Identify potential market inefficiency based on academic research or empirical observation
Backtest
Rigorously test the hypothesis across multiple markets, time periods, and market regimes
Validate
Out-of-sample testing and stress testing under extreme market conditions
Deploy
Systematic implementation with real-time monitoring and continuous improvement
Frequently Asked Questions
Common questions about our systematic investment approach and how we generate alpha for institutional investors.
""We are differentiated by our quantitative rigor, depth of research, and entrepreneurial culture. This combination enables SINTRO to pursue opportunities and remain nimble in an ever-changing market environment.
