About AI-Stock
We built AI-Stock because retail investors in India deserve the same data-driven analysis that institutional desks use — without the complexity.
Our mission
Institutional fund managers have armies of analysts, Bloomberg terminals, and proprietary models. A retail investor sitting in Bangalore or Surat has none of that. AI-Stock bridges that gap by packaging the same kind of multi-signal analysis into a simple daily digest: three actionable stock picks with a clear entry, target, and stop-loss.
We are not a SEBI-registered research analyst. We are an engineering team that built a model, back-tested it, and now publish its daily output transparently — including every outcome, hit or miss, on our public track record page.
How the model works
1. Technical signals
We compute a suite of price-derived indicators for every NSE stock — including RSI (Relative Strength Index) to gauge momentum and overbought/oversold conditions, ATR (Average True Range) to size stops relative to volatility, moving-average crossovers, volume-weighted averages, and proprietary momentum scores derived from recent price action. Stocks that fail basic liquidity filters (average daily volume < ₹2 Cr) are removed before scoring.
2. Fundamental screening
Technical signals are overlaid with fundamental filters pulled from quarterly filings: revenue growth (YoY and QoQ), debt-to-equity ratios, return on equity, and operating margin trends. A stock with strong technicals but deteriorating fundamentals receives a penalty in the composite score, reducing the chance it surfaces as a top pick.
3. News sentiment (FinBERT)
Each morning we fetch recent Google News headlines for every stock in scope. These headlines are passed through FinBERT — a BERT-based transformer fine-tuned on financial text — which assigns a sentiment score (positive, neutral, negative) to each article. The aggregate sentiment is folded into the composite score as a third signal layer.
The scoring system
Each stock receives a composite score from 0 to 100. The XGBoost model was trained on historical NSE data with a label that captures whether the stock outperformed the Nifty 50 over the subsequent 5 trading days. A score above 65 is required for a stock to be classified as STRONG BUY and eligible to appear as a daily pick. The three highest-scoring eligible stocks are selected each day.
Confidence tiers
All three data sources — technical, fundamental, and sentiment — agree on a bullish signal. Highest-confidence picks.
Technical signal is strong and at least one of fundamental or sentiment supports the thesis. Moderate confidence.
Signal driven by technical indicators alone. Fundamental or sentiment data was unavailable or neutral. Lower confidence — consider smaller position sizes.
Risk disclaimer
AI-Stock is not registered with the Securities and Exchange Board of India (SEBI) as a research analyst or investment advisor. The signals published by AI-Stock are for informational and educational purposes only and do not constitute investment advice, a solicitation to buy or sell securities, or a recommendation. Investing in equities involves market risk, including the possible loss of principal. Past accuracy of picks does not guarantee future performance. Users are solely responsible for their own investment decisions and should consult a SEBI-registered investment advisor before making any investment.