Bourse
EN
Menu
Radar
Pricing
Developers / API

Jim Cramer’s calls.
Scored, not just repeated.

Bourse reads CNBC’s “Mad Money”, lightning round and “Final Trades” articles, sorts every mention into buy, sell or hold with AI, and tracks what happened next.

Every call, on the record.

01Mad Money calls

Every stock Cramer mentions, with the reason he gave and the date of the show.

02Lightning round

The fast-fire buy and sell answers to viewers, one line per stock.

03CNBC Final Trades

The closing picks of CNBC’s guests, separately from Cramer.

04Inverse Cramer

A strategy that bets against his calls - and one that follows them - so you can see who wins.

The record. Real backtests.

StrategyReturnS&P 500SharpeMax drawdownSinceLive since publication
CNBC Final Trades−4.8%−3.2%-3.83−6.3%2026-10-30−9.1% since 2026-11-13, max drawdown −9.1%

Updated 2026-11-18. Simulated on historical data with 0.1% costs per trade, before taxes; returns are cumulative since the start date. The live column starts on the day the strategy was published and is never recalculated, with the same 0.1% costs. Past results do not predict future ones.

From the studio to a scorecard.

  1. 1Episode airs

    CNBC publishes a recap of the show and the lightning round.

  2. 2AI classifies

    Each stock mention is sorted into buy, sell or hold, with the reason in one line.

  3. 3Matched

    Names are matched to listed tickers; non-stock mentions are dropped.

  4. 4Scored

    The Cramer strategies show what following or fading him would have returned.

Calls as data. For your own tests.

Every record has these fields, in the app and in the Bourse API as JSON or CSV.

dateshowpersontickercompanycallreasonurl
Endpoint documentation
api.bourse.pl
$ curl "https://api.bourse.pl/v1/tv-picks?limit=3" \
    -H "Authorization: Bearer $BOURSE_KEY"

# JSON with fields:
date, show, person, ticker, company …

About the show. And the data.

Does Inverse Cramer really work?

The strategy page shows its backtest since 2021 against the S&P 500, with drawdown and Sharpe. Past results do not guarantee future ones.

How do you know if it was a buy or a sell?

An AI model reads the article text around each mention and returns buy, sell or hold. Unclear mentions are marked hold.

Booyah or bust? Check the score.

Bourse provides financial data and editorial information, parts of which are generated by AI. This page is for general education only. It is not personalised investment advice or a recommendation to buy or sell any financial instrument. Make your own decisions.