Test Period
The test period for evaluating the accuracy of cryptocurrency price predictions is from July 14, 2023, 00:00:00, to July 21, 2023, 00:00:00.
Introduction
In this report, we present the accuracy results of the AI Assistant's predictions for various cryptocurrencies, including BTC, ETH, XRP, and DOGE. The accuracy is evaluated for different risk appetites, namely Cautious, Balanced, and Adventurous, and at different prediction intervals of 15 minutes, 30 minutes, 1 hour, 3 hours, and 6 hours.
Result
1. 15 Minute Accuracy:
| Coin | Risk App | Accuracy | Attended Features |
|---|---|---|---|
| BTC | Cautious | 52.71% | Based on social news |
| BTC | Balanced | 58.16% | Mostly attended On-chain features |
| BTC | Adventurous | 79.84% | Well-predicted price |
| ETH | Cautious | 75.07% | Mostly attended Technical Indicators |
| ETH | Balanced | 77.71% | Mostly attended Technical Indicators |
| ETH | Adventurous | 83.43% | Well-predicted price |
| XRP | Cautious | 65.93% | Based on social news |
| XRP | Balanced | 48.99% | Mostly attended On-chain features |
| XRP | Adventurous | 60.95% | Well-predicted price |
| DOGE | Cautious | 64.65% | Well-predicted price |
| DOGE | Balanced | 66.27% | Mostly attended On-chain features |
| DOGE | Adventurous | 66.27% | Mostly attended On-chain features |
2. 30 Minute Accuracy:
| Coin | Risk App | Accuracy | Attended Features |
|---|---|---|---|
| BTC | Cautious | 51.17% | Mostly attended On-chain features |
| BTC | Balanced | 53.82% | Mostly attended On-chain features |
| BTC | Adventurous | 58.19% | Well-predicted price |
| ETH | Cautious | 57.31% | Based on social news |
| ETH | Balanced | 57.28% | Mostly attended Technical Indicators |
| ETH | Adventurous | 59.92% | Well-predicted price |
| XRP | Cautious | 62.96% | Based on social news |
| XRP | Balanced | 60.56% | Based on social news |
| XRP | Adventurous | 56.92% | Mostly attended On-chain features |
| DOGE | Cautious | 53.44% | Based on social news |
| DOGE | Balanced | 51.83% | Mostly attended Technical Indicators |
| DOGE | Adventurous | 63.55% | Based on social news |
3. 1 Hour Accuracy:
| Coin | Risk App | Accuracy | Attended Features |
|---|---|---|---|
| BTC | Cautious | 66.53% | Mostly attended On-chain features |
| BTC | Balanced | 67.07% | Mostly attended On-chain features |
| BTC | Adventurous | 71.65% | Mostly attended On-chain features |
| ETH | Cautious | 63.77% | Mostly attended Technical Indicators |
| ETH | Balanced | 67.26% | Mostly attended Technical Indicators |
| ETH | Adventurous | 73.7% | Mostly attended On-chain features |
| XRP | Cautious | 90.12% | Based on social news |
| XRP | Balanced | 67.13% | Based on social news |
| XRP | Adventurous | 57.03% | Well-predicted price |
| DOGE | Cautious | 54.85% | Based on social news |
| DOGE | Balanced | 52.73% | Based on social news |
| DOGE | Adventurous | 65.55% | Based on social news |
4. 3 Hour Accuracy:
| Coin | Risk App | Accuracy | Attended Features |
|---|---|---|---|
| BTC | Cautious | 51.39% | Mostly attended On-chain features |
| BTC | Balanced | 55.56% | Mostly attended On-chain features |
| BTC | Adventurous | 59.07% | Well-predicted price |
| ETH | Cautious | 56.51% | Mostly attended Technical Indicators |
| ETH | Balanced | 57.89% | Mostly attended Technical Indicators |
| ETH | Adventurous | 61.18% | Well-predicted price |
| XRP | Cautious | 59.88% | Based on social news |
| XRP | Balanced | 57.41% | Based on social news |
| XRP | Adventurous | 56.32% | Mostly attended On-chain features |
| DOGE | Cautious | 54.85% | Based on social news |
| DOGE | Balanced | 52.73% | Based on social news |
| DOGE | Adventurous | 65.55% | Based on social news |
5. 6 Hour Accuracy:
| Coin | Risk App | Accuracy | Attended Features |
|---|---|---|---|
| BTC | Cautious | 51.39% | Mostly attended On-chain features |
| BTC | Balanced | 55.56% | Mostly attended On-chain features |
| BTC | Adventurous | 59.07% | Well-predicted price |
| ETH | Cautious | 56.51% | Mostly attended Technical Indicators |
| ETH | Balanced | 57.89% | Mostly attended Technical Indicators |
| ETH | Adventurous | 61.18% | Well-predicted price |
| XRP | Cautious | 59.88% | Based on social news |
| XRP | Balanced | 57.41% | Based on social news |
| XRP | Adventurous | 56.32% | Mostly attended On-chain features |
| DOGE | Cautious | 54.85% | Based on social news |
| DOGE | Balanced | 52.73% | Based on social news |
| DOGE | Adventurous | 65.55% | Based on social news |
Average Accuracy for Different Risk Appetites
- For Cautious users, the average accuracy of the Signals among all
coins was 60.15%.
- For Balanced users, the average accuracy of the Signals among all
coins was 59.17%.
- For Adventurous users, the average accuracy of the Signals among
all coins was 65.16%.
Overall Average Accuracy for All Time Intervals
The overall average accuracy of the Signals among all coins, considering all time intervals, is 61.24%.
Conclusion
The AI's accuracy in predicting cryptocurrency prices varies based on the risk appetite and the time interval of predictions. The AI performed relatively better for Adventurous users compared to Cautious and Balanced users. It achieved the highest average accuracy for the Adventurous risk appetite, indicating that users willing to take higher risks may benefit more from the AI's predictions. However, the overall average accuracy for all risk appetites and time intervals was moderate, suggesting that further improvements could be made to enhance the accuracy of the Signal's predictions.
Note: The accuracy results and conclusions provided in this report are based on historical data, and cryptocurrency markets are highly volatile and subject to rapid changes. Therefore, these results may not be indicative of future performance. Users are advised to exercise caution and perform their own research before making any financial decisions based on AI predictions.
Market terms used here
CryptoCrispy reports score cryptocurrency trading signals on USDT spot pairs — Bitcoin (BTC), Ethereum (ETH), and altcoins such as SOL, XRP, BNB, and RENDER. Published Telegram buy/sell alerts are counted separately from in-app AI Assistant suggestions.
- Take-profit (TP1–TP5) — staged profit targets on a long or short. A target hit counts only after the signal is decided.
- Stop-loss (SL) — risk exit. A stop is a loss, not a timeout.
- Hit rate / TP vs SL — wins among decided signals. Open or no-result (NR) rows are not wins.
- AI Assistant — in-app long/short suggestions. Modes: default mix, technical analysis, social sentiment, and AI/on-chain data.
- Telegram Official Signals — published channel alerts, often a rolling last-40 window.
- Core vs tactical — investor-book split: persistent hold versus a smaller rotating sleeve.
- ROI — return after pairing BUY then SELL on the same symbol, fees subtracted, on trading pages.
- Risk appetite — separate risk modes; the headline is sample-weighted, not the best bucket.
See how these numbers are counted and the crypto trading reports library.