How to Use Fundamentals AND Technicals in a Single Trading Model

Most traders pick a side: fundamental or technical. Fundamental traders read balance sheets and earnings reports. Technical traders read charts and momentum signals. Quantitative trading shows that the real edge comes from combining both — plus data most retail traders never think to include, like GDP growth trends, sector earnings revisions, and macro indicators. Here's how it works and why it matters.

The False Divide Between Fundamental and Technical

The debate between fundamental and technical analysis has gone on for decades. In practice, the traders who generate consistent returns often use both — they want to buy a company with strong fundamentals that is also showing price momentum, not just one or the other.

A machine learning trading model makes this combination systematic. Instead of manually checking whether a stock has a good P/E ratio AND is trending above its moving average AND has recent earnings beats, the model considers all of these factors simultaneously and weights them based on their historical predictive power.

What "Fundamentals" Really Means in a Trading Model

When quant traders talk about fundamentals, they mean quantitative representations of company health and valuation — not reading annual reports:

• Valuation ratios: P/E, P/S, EV/EBITDA, price-to-book. Are you paying a fair price for the business?
• Earnings metrics: EPS growth, earnings surprise vs. estimates, margin trends. Is the business actually improving?
• Revenue data: revenue growth rate, revenue acceleration, sales per share. Is demand for their product growing?
• Profitability: return on equity, return on assets, free cash flow yield. Is the company generating real returns?

These features have documented long-term predictive power because they reflect real business performance, not just market sentiment.

What "Technicals" Means in a Systematic Model

Technical features in a systematic model are not about drawing lines on charts. They are quantitative signals derived from price and volume history:

• Momentum: 12-month return, return relative to sector, return relative to market
• Trend: distance from 52-week high, position relative to moving averages
• Volatility: average true range, realized volatility, beta
• Volume signals: relative volume, volume trend

Momentum in particular has one of the strongest track records in academic finance — the tendency of recent winners to continue outperforming over 3–12 month horizons is documented across decades and geographies.

The Features Most Retail Traders Never Think to Include

Beyond standard fundamentals and technicals, there's a category of macro and contextual features that dramatically improve model performance — and that most retail traders have never considered:

• GDP growth by sector: technology companies don't respond to GDP the same way industrials do. Sector-level macro context matters.
• Interest rate environment: high-growth stocks behave very differently in a rising rate environment vs. a falling rate environment. A model that knows the rate regime makes better decisions.
• Sector earnings revision trends: when analysts are upgrading earnings estimates across an entire sector, stocks in that sector have tailwinds. This is a macro signal that benefits individual stock picks.
• Relative sector strength: is your stock outperforming its sector, or just riding sector momentum? These are very different signals.

Including macro context turns a stock-picker model into a model that understands the environment it's operating in.

Why the Combination Outperforms Either Alone

Value and momentum are often negatively correlated. During growth bull markets, cheap stocks underperform and momentum stocks outperform. During reversals and corrections, the opposite tends to happen. A model that combines both gets the benefit of each signal in the right environment, while the other provides a floor when one is struggling.

The academic term for this is "factor diversification," and it's one of the core reasons why institutional quant funds build multi-factor models rather than betting on a single signal.

How Quant-Builder.ai Gives You All of This

Building a combined fundamental + technical + macro model from scratch requires sourcing data from multiple providers, aligning it by date and ticker, ensuring point-in-time accuracy, and engineering features from raw data. For a professional data team, that's months of work.

Quant-Builder.ai has already done it. The platform provides 600+ pre-built features across all categories — valuation, earnings quality, growth, momentum, technicals, macro — across 3,000+ stocks and 30 years of point-in-time data. You pick the features you want to include, configure your model, and the platform trains, validates, and deploys it. No code. No data pipeline. No PhD required.

The model output shows you which features actually drove the predictions — so you can see whether your model is leaning on valuation, momentum, or macro signals, and refine it accordingly.

See real model walkthroughs — an All Stocks model and a Consumer Cyclical sector model:

Quant-Builder.ai — Simplifying Quant Trading: Try a Free Demo at quant-builder.ai/learn

Quant-Builder.ai — Simplifying Quant Trading: Try a Free Demo at quant-builder.ai/learn

Build a Multi-Factor Model Today

The free demo at Quant-Builder.ai lets you build a model combining fundamentals, technicals, and macro data — and run a full walk-forward backtest — before spending anything. Plans start at $25/month when you're ready to trade it live.