--- title: "Position Sizing | RupeeCase Learn" description: "How much to allocate to each stock | equal weight, inverse volatility, Kelly criterion, and conviction weighting." source_url: "https://www.rupeecase.com/learn/path-4/module-4-2-position-sizing" --- Skip to main content [Learn](/learn)›[Path 4: Portfolio Construction](/learn/path-4)›Module 4.2 # Position Sizing The most underappreciated decision in portfolio construction | how much to allocate to each stock. Equal weight, inverse volatility, Kelly criterion, and why simplicity usually wins. TK Tanmay Kurtkoti Founder & CEO, RupeeCase ⏱ 13 min read ⟳ Updated 14 Jun 2026 ◆ Advanced You've selected your stocks using a systematic factor signal. Now: how much do you put in each one? This question gets far less attention than stock selection | but it matters enormously. The same 30-stock portfolio, positioned differently, can have a max drawdown of 30% or 50%. Same stocks, different sizing. There are four main approaches to position sizing in systematic equity portfolios. Each makes different assumptions about what you know | and more importantly, what you don't know. 10% Max single stock cap I use 2% Risk budget per trade 20% Max sector exposure 0.5 Half Kelly multiplier default Position sizing is the quiet decision that changes everything. Same 30 stocks, two different size rules, and the drawdown gap between them can be 15 percentage points over a full cycle. 1 Capital available Total portfolio value after cash reserve carve out 2 Risk per position Target volatility divided by expected stock vol 3 Apply caps Single stock 10%, sector 20%, top 5 cap 45% 4 Round to lot Whole shares only, no partial NSE lots 5 Execute TWAP Spread into 3 to 5 slices to minimise impact My position sizing flow. Step 3 is where most discretionary investors skip. Caps are unromantic, but they are what keeps one bad thesis from wrecking the year. Risk budget of 2% per position * Core systematic 70% * Satellite tactical 20% * Cash buffer 10% Top 5 positions share in portfolio * Position 1 cap 10% * Position 2 cap 10% * Position 3 cap 9% * Positions 4 5 cap 16% A 10 stock RupeeCase Nifty portfolio with 10% single stock cap means your top conviction name cannot sink the whole book, even on a 40% single stock drawdown. Portfolio drawdown by sizing method (Indian equity backtest 2008 to 2024) Equal weight 38% Market cap weighted 42% Inverse volatility 31% Vol target 12% 26% Full Kelly (overfit) 58% Full Kelly sounds optimal in theory. In Indian markets where estimation error on expected return is large, it is a very fast way to lose 50%. Half Kelly or volatility targeting is where I park in practice. From my notebook October 2017, I had built a small cap basket with 12 names, 8% each. The signal was genuinely strong. But I skipped the sector cap check. Seven of the twelve were micro finance or housing finance. When IL and FS defaulted in September 2018, the basket dropped 51% in 4 months while the Nifty fell 14%. Same signal, same stock picks, same entry. But the missing 20% sector cap cost me 37 percentage points of drawdown. Since that quarter I have never sized a single stock without running sector and factor overlap checks first. Position sizing is not where you save time. ## The four approaches Equal Weight Simple Weight(i) = 1 / N Every stock in the portfolio gets the same allocation. If you hold 30 stocks, each gets 1/30 = 3.33%. No assumptions about which stock is "better" than another. Maximum simplicity, maximum diversification across selections. * Requires no additional inputs beyond stock selection * Naturally overweights small-cap stocks relative to market cap weighting | provides size factor exposure * Strong academic evidence that equal weight frequently matches or beats optimised weights out-of-sample * High-volatility stocks get the same weight as low-volatility stocks | can lead to concentration of risk in a few volatile names ✓ RupeeCase default | use this unless you have a specific reason to deviate Inverse Volatility Weight Moderate Weight(i) = (1/σⅧ) / ∑(1/σⅧ) Each stock's weight is inversely proportional to its 1-year daily volatility. Less volatile stocks get higher allocations. Ensures that each stock contributes roughly equally to portfolio risk, even if they have different absolute volatilities. * Reduces the "risk concentration" problem of equal weight | a 50% annualised volatility stock no longer dominates portfolio risk * Empirically: improves Sharpe ratio vs equal weight in most markets and time periods * More expensive | requires calculating volatility for each stock and recomputing weights each rebalance * Can inadvertently create high concentration in defensive/low-vol sectors if not capped ✓ Use for multi-factor strategies where vol varies significantly across selected stocks Market Cap Weight Moderate Weight(i) = MarketCap(i) / ∑MarketCap Weight each stock by its market capitalisation relative to the total portfolio market cap. Larger companies get higher allocations. This is how index funds work | the Nifty 50 and Nifty 500 are market cap weighted. * Minimises trading | large stocks don't drift as much, so rebalancing is less frequent * Concentrates portfolio in the largest stocks | can mean 30 to 40% in 5 stocks * Systematically underweights smaller companies that may have higher factor scores * For factor strategies: not recommended | defeats the purpose of factor selection by reintroducing market-cap bias ⚠ Avoid for factor strategies | use only if replicating an index Kelly Criterion / Signal-Scaled Complex f* = (p × b − q) / b The Kelly criterion gives the theoretically optimal fraction of capital to bet based on edge and odds: f* is the optimal fraction, p is the probability of winning, b is the payoff ratio, q = 1-p is probability of losing. In practice, full Kelly is far too aggressive | most systematic traders use "fractional Kelly" (25 to 50% of the Kelly fraction). * Theoretically optimal for long-run capital growth if edge estimates are correct * Requires accurate estimates of win rate and payoff ratio for each position | very hard to get right for equity strategies * Full Kelly leads to extreme concentration and large drawdowns in practice * Useful conceptually for understanding bet sizing | not practical for multi-stock factor portfolios ✗ Too complex for most factor strategies | conceptual value only ## Worked example: equal vs inverse volatility Let's say your momentum strategy selects 5 stocks with these annual volatilities: | Stock | Volatility (1Y) | Equal Weight | Inverse Vol Weight | | --- | --- | --- | --- | | Reliance | 22% | 20% | 25.2% | | Bajaj Finance | 35% | 20% | 15.8% | | Tata Motors | 48% | 20% | 11.5% | | Infosys | 26% | 20% | 21.3% | | Asian Paints | 20% | 20% | 27.7% | | Portfolio Vol (approx) | | ~30% (dominated by Tata Motors) | ~24% (more balanced) | In the equal weight portfolio, Tata Motors (48% vol) contributes a disproportionate share of portfolio variance despite being only 20% of capital. Inverse volatility weighting corrects this | Tata Motors drops to 11.5% weight while Reliance and Asian Paints (more stable) get higher weights. **The practical tradeoff:** Inverse volatility weighting produces smoother returns but requires a bit more complexity at each rebalance. For portfolios of 20+ stocks with similar volatilities, the difference narrows significantly | equal weight is usually good enough. For concentrated portfolios (10 to 15 stocks) or those that consistently include a mix of volatile growth stocks and stable compounders, inverse vol weight meaningfully improves the ride. ## Position sizing constraints Regardless of the weighting scheme, practical constraints prevent extreme concentration: * **Maximum single-stock weight** | typically 10 to 15% for a 20-stock portfolio, 5 to 8% for a 30-stock portfolio. Prevents any single stock from dominating performance or drawdown. * **Maximum sector weight** | typically 25 to 35%. Prevents a sector-driven momentum signal from putting 50%+ into, say, IT or banking in a single period. * **Minimum position size** | typically 1 to 2% of portfolio. Positions smaller than this generate trading friction that exceeds any informational value. * **Liquidity constraint** | position size should not exceed 5 to 10% of the stock's average daily traded volume. Prevents market impact on entry and exit. Position sizing on RupeeCase RupeeCase strategies default to **equal weight** with a single-stock cap of 10% and a sector cap of 35%. The inverse volatility weighting option is available in the Backtester | toggle it on to see how it changes the Sharpe ratio and max drawdown for any strategy. For most Nifty 500 momentum strategies, inverse vol weight improves Sharpe by roughly 0.1 to 0.2 over a 10-year backtest. Explore at [invest.rupeecase.com](https://invest.rupeecase.com). Test position sizing on RupeeCase Compare equal weight vs inverse volatility weight | side by side backtest See the Sharpe and drawdown difference instantly. [Start free →](https://invest.rupeecase.com/signup) ## Glossary Key terms from this module Equal weightAllocating 1/N of capital to each stock in the portfolio. Simplest and most robust weighting scheme | each position has equal capital allocation. Inverse vol weightAllocating in inverse proportion to each stock's volatility. Less volatile stocks get higher weights, ensuring more equal contribution to portfolio risk. Kelly criterionA formula for optimal bet sizing based on edge and odds. Theoretically optimal for long-run growth but requires accurate edge estimates and typically produces extreme concentration. Risk contributionThe share of total portfolio variance contributed by each position. In equal weight, high-volatility stocks contribute disproportionately more risk than their capital weight suggests. Sector capA maximum weight constraint limiting how much of the portfolio can be in any single sector | typically 25 to 35%. Prevents sector-driven signals from creating extreme concentration. TK A note from the author Why this matters Position sizing is the single most underappreciated lever in portfolio construction. I have seen brilliant stock-selection systems ruined by naive equal-weighting, and mediocre signals rescued by intelligent sizing. In Indian markets, where liquidity varies dramatically between large-caps and small-caps, getting your position sizes right is not optional | it is the difference between a strategy that survives and one that blows up. TK Tanmay Kurtkoti Founder & CEO, RupeeCase · 17 years systematic trading · QC Alpha RC **Want to put this into practice?** RupeeCase is the systematic investing terminal built around everything you're learning here, factor scores, strategy backtests, portfolio construction for Indian markets. [Explore the terminal →](https://invest.rupeecase.com) #### Sources & further reading * → DeMiguel, V. et al. (2009). Optimal Versus Naive Diversification. Review of Financial Studies. (Equal weight vs optimised) * → Kelly, J.L. (1956). A New Interpretation of Information Rate. Bell System Technical Journal. (Original Kelly criterion paper) * → Thorp, E. (2006). The Kelly Criterion in Blackjack, Sports Betting, and the Stock Market. Handbook of Asset and Liability Management. * → [NSE India Research — Portfolio Construction Resources](https://www.nseindia.com/research) ### Quick check, Module 4.2 0 correct · 0 answered ✓ Module complete! Next module unlocked. 🎉 Module 4.2 complete 3 correct. Continue to Module 4.3 when ready. 🎓 Spread the knowledge This course is free. Help someone else learn about Position Sizing, share it with one person who needs this. 📋 Suggested LinkedIn post, copy & paste Just completed Module 4.2 of Tanmay Kurtkoti's free investing course on RupeeCase. Learning about Position Sizing. Completely free at rupeecase.com/learn Copy text Share on X Post on LinkedIn Copy link Research Lab Qualifier Path 4, Module 2 of 5 done, complete all 5 + path test to unlock [Explore terminal →](https://invest.rupeecase.com) ✅ 4.1 MPT → 📍 4.2 Position Sizing → 4.3 Rebalancing → 4.4 Performance → 4.5 Risk Mgmt [← Previous](module-4-1-modern-portfolio-theory.html) Previous, Module 4.1 Modern Portfolio Theory Calculator ### Position Size Calculator Decide how many shares to buy based on portfolio size, risk per trade and stop distance. Portfolio (INR)Risk per trade (%)Entry price (INR)Stop loss price (INR) Quick check, Module 4.2 ## 3 questions. Get 2 right to mark this module complete. 0 of 3 answered ✓ Module complete. Keep going. Up next, Module 4.3 Rebalancing Strategies Calendar vs threshold rebalancing, the cost-return tradeoff of frequency, and the discipline of selling what's working to buy what's lagged. [Continue →](module-4-3-rebalancing-strategies.html)