TildAlice – Tech Blog for Developers
Python, AI, Deep Learning, Data Analysis, Computer Vision, Reinforcement Learning โ tips and tutorials
Latest Posts
-
ML Stock Prediction: Why Most Fail and What Works
Most ML stock models fail live trading within weeks. Here's what survives transaction costs, regime shifts, and the reality of slippage.
-
Risk Management and Portfolio Optimization Techniques in Python
VaR underestimates tail risk, Markowitz explodes on estimation error. Fix it with shrinkage estimators and Kelly criterion position sizing.
-
Trie for Fast String Search: Autocomplete in Python
Build a trie in Python that beats naive search by 40x on prefix queries. Covers autocomplete, Word Search II, and deletion edge cases.
-
Backtesting Frameworks: Building Your First Trading Strategy
Most backtests lie about profitability through lookahead bias. Build a point-in-time engine that doesn't cheat on order fills or data access.
-
Quant Feature Engineering with Pandas and TA Indicators
Why shift(1) is the most important line in your feature engineering pipeline โ and how to avoid the temporal leakage that kills strategies.
-
Data Collection and Preprocessing for Quant Trading in Python
Stock split adjustments, survivorship bias, and timestamp alignment pitfalls that corrupt your trading data โ with yfinance and Parquet fixes.
-
Getting Started with Quantitative Investment in Python
Build a quant trading infrastructure in Python: data pipelines, log return calculations, and backtesting that includes transaction costs.
-
Bayesian A/B Testing: Beta-Binomial for Small Samples
Get actionable A/B test results with 50 conversions, not 5,000. Beta-Binomial conjugacy gives you posteriors and expected loss in minutes.