Sabitlenmiş Tweet
Financial Systems Engineering
324 posts

Financial Systems Engineering
@thefselab
Computational Finance | FinTech | AI in Finance | Financial Systems Engineering
Katılım Mart 2012
80 Takip Edilen36 Takipçiler

Finance today depends on software.
Software depends on infrastructure.
Infrastructure depends on architecture.
Yet we still teach finance largely through economics, mathematical models, and financial instruments.
If modern finance is becoming critical digital infrastructure...
Which discipline should be responsible for engineering it?
Financial Engineering?
Software Engineering?
Systems Engineering?
Something entirely new?
Curious how practitioners across finance, technology, and regulation think about this.
English

Edge compounds only after trust removes discretion; until then, your biggest source of alpha is often your biggest source of variance.
Goshawk Trades@GoshawkTrades
good systems compound in trading. backtest a strategy properly. trust the results enough to go live. follow every signal because you trust the process. consistent execution compounds returns. returns give you capital to add a second strategy. two uncorrelated strategies smooth your equity curve. smoother curve means less panic. less panicking means you never override the system. the first strategy you trust completely is the hardest. everything after that compounds.
English

@GoshawkTrades The missing layer is execution. A strategy can be statistically sound yet fail if fills; latency, slippage, or liquidity assumptions differ from the backtest. Trust compounds only when both the signal and the market plumbing behave as expected.
English

good systems compound in trading.
backtest a strategy properly. trust the results enough to go live. follow every signal because you trust the process. consistent execution compounds returns. returns give you capital to add a second strategy. two uncorrelated strategies smooth your equity curve. smoother curve means less panic. less panicking means you never override the system.
the first strategy you trust completely is the hardest. everything after that compounds.
English

@quantbeckman The key implication for financial modeling is identifiability. If multiple latent state configurations produce the same observed prices, calibration alone cannot recover the true market state. You need structural constraints or additional data beyond price history.
English


