Build strategies from rule blocks, score stocks with factors, use math for diversification and portfolio optimization, then puncture backtest illusions with out-of-sample testing.
For: learners who know technical analysis and backtesting and want to trade in a systematic, rules-based way
This course uses ideas from the courses below (optional; you can start right away).
Turn "gut feel" into rules: buy when one condition is true, sell when another is. Snap a few blocks together and let historical prices give you the answer.
Do cheap stocks, strong-trending stocks and high-quality stocks do better on average? Sort stocks into five groups by a factor and the answer is plain to see.
The more assets you hold that don't move in perfect sync, the less your portfolio swings. But correlation sets the limit on how far diversification can go.
How should you mix stocks, bonds and gold? Plot every combination of weights, and the top-left edge is the efficient frontier: the highest return for each level of risk.
Picking the best settings on historical data is easy. The hard part is whether they still work on data they've never seen. Walk-forward testing mimics the real process of choosing settings first, then trading.
A strategy that returns 15% a year in a backtest may have nothing left after fees and slippage. The more you trade, the more costs eat.
Stocks that did well over the past few months tend to stay a bit stronger; but those that just shot up last month often give it back the next. The lookback period decides whether you're buying momentum or reversal.
60% stocks / 40% bonds looks balanced, but stocks are far more volatile, so over 90% of the portfolio's risk actually comes from stocks. Risk parity makes each asset class contribute the same amount of risk.