Cryptocurrency markets move rapidly and are influenced by multiple factors such as price momentum, market capitalization, trading activity, and overall market sentiment. Monitoring hundreds of crypto assets manually can be inefficient because market conditions change continuously.

This project develops a MarketFlow AI Crypto Trading Scanner that analyzes trending crypto assets using automated scoring and visualization. The system combines market trend data, momentum indicators, asset ranking, and sentiment analysis to identify potential market opportunities.

The scanner workflow consists of five main stages:

• API configuration and library preparation

• Trending crypto asset data processing

• Trader score calculation

• Crypto momentum heatmap visualization

• Automated trading analysis report

The system is developed using Python with Requests for API integration, Pandas for data processing, NumPy for numerical operations, Matplotlib and Seaborn for visualization. The project retrieves market data from MarketFlow API and transforms raw crypto information into a structured trading intelligence system. marketflow_ai_crypto_trading_sc…

Cell 1 — Import Library and API Configuration

The first cell prepares the Python environment and configures API authentication. The required libraries are imported for data retrieval, processing, and visualization.

import requests
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

API_KEY = "YOUR_API_KEY"

HOST = "marketflow-all-in-one-market-finance-api.p.rapidapi.com"

headers = {
    "x-rapidapi-host": HOST,
    "x-rapidapi-key": API_KEY
}

print("Library siap")

marketflow_ai_crypto_trading_sc…

Cell 2 — Global Heatmap and Trending Crypto Data

The second cell processes trending cryptocurrency data into a Pandas DataFrame.

The dataset contains trending assets that will become the analysis universe for momentum scoring.

# =========================
# TRENDING DATA PROCESSING
# =========================

trend_df = pd.DataFrame(
    trend_data["coins"]
)


print("Jumlah Trending Asset:", len(trend_df))

display(
    trend_df.head()
)

marketflow_ai_crypto_trading_sc…

Cell 3 — Trader Score Model

The third cell creates a scoring model to evaluate crypto assets.

The scoring mechanism uses three main indicators:

• 24-hour price momentum

• Market capitalization ranking

• Trading volume availability

The final score ranks assets based on short-term trading attractiveness.

The scoring logic:

• Price change > 5% → +50 points

• Price change > 0% → +25 points

• Negative momentum → -20 points

• Market rank ≤ 50 → +30 points

• Available volume → +20 points

marketflow_ai_crypto_trading_sc…

# ==================================
# TRADER SCORE MODEL
# ==================================


# cek data
if trend_df.empty:

    print("ERROR: trend_df kosong. Jalankan ulang Cell 2.")

else:


    def trader_score(row):

        score = 0


        # Momentum
        change = row.get(
            "price_change_24h",
            0
        )


        if change > 5:
            score += 50

        elif change > 0:
            score += 25

        else:
            score -= 20



        # Market rank
        rank = row.get(
            "market_cap_rank",
            999
        )


        if rank <= 50:
            score += 30



        # Volume
        volume = row.get(
            "volume",
            ""
        )


        if volume != "":
            score += 20



        return score



    trend_df["Trader_Score"] = trend_df.apply(
        trader_score,
        axis=1
    )



    trend_df = trend_df.sort_values(
        "Trader_Score",
        ascending=False
    )


    display(
        trend_df[
            [
            "symbol",
            "name",
            "price_change_24h",
            "market_cap_rank",
            "Trader_Score"
            ]
        ].head(10)
    )

Cell 4 — Crypto Momentum Heatmap

The fourth cell visualizes crypto momentum conditions using a heatmap.

The visualization compares:

• 24-hour price change

• Trader Score

The heatmap provides a quick overview of assets with stronger momentum conditions.

marketflow_ai_crypto_trading_sc…

# =====================================
# MARKET MOMENTUM HEATMAP
# =====================================

import matplotlib.pyplot as plt
import seaborn as sns


# Pastikan data tersedia

if trend_df.empty:

    print("Data trending kosong. Jalankan Cell 2 dan Cell 3 terlebih dahulu.")

else:


    heatmap_data = trend_df[
        [
            "symbol",
            "price_change_24h",
            "Trader_Score"
        ]
    ].copy()



    # Set symbol sebagai index

    heatmap_data = heatmap_data.set_index(
        "symbol"
    )


    plt.figure(
        figsize=(10,6)
    )


    sns.heatmap(
        heatmap_data,
        annot=True,
        fmt=".2f",
        cmap="RdYlGn",
        linewidths=0.5
    )


    plt.title(
        "Crypto Momentum Heatmap"
    )


    plt.xlabel(
        "Indicator"
    )


    plt.ylabel(
        "Asset"
    )


    plt.show()

Cell 5 — Market Flow AI Trading Report

The final cell generates an automated market intelligence report.

The system identifies:

• Top momentum opportunity

• Market bullish ratio

• Overall sentiment condition

• Trading checklist

Market sentiment classification:

• Bullish → Positive assets ≥ 70%

• Bearish → Positive assets ≤ 40%

• Neutral → Between those ranges

# =====================================
# MARKET FLOW TRADING REPORT
# =====================================


print("="*65)
print("          MARKET FLOW AI TRADING REPORT")
print("="*65)



if trend_df.empty:

    print(
        "Tidak ada data untuk dianalisis."
    )


else:


    # Ranking Top Opportunity

    top_asset = trend_df.iloc[0]


    print(
f"""
TOP MOMENTUM OPPORTUNITY

Symbol :
{top_asset['symbol']}

Name :
{top_asset['name']}

24H Change :
{top_asset['price_change_24h']:.2f}%

Market Rank :
#{top_asset['market_cap_rank']}

Trader Score :
{top_asset['Trader_Score']}/100


"""
    )



    # Market Sentiment

    bullish = (
        trend_df["price_change_24h"] > 0
    ).sum()


    total = len(trend_df)


    bullish_ratio = (
        bullish / total
    )*100



    if bullish_ratio >= 70:

        sentiment = "BULLISH"

    elif bullish_ratio <= 40:

        sentiment = "BEARISH"

    else:

        sentiment = "NEUTRAL"



    print(
f"""
MARKET SENTIMENT

Positive Asset :
{bullish}/{total}

Bullish Ratio :
{bullish_ratio:.2f}%

Condition :
{sentiment}


"""
    )



    # Trading Guidance

    print(
"""
TRADER CHECKLIST

ENTRY CONDITION:
✓ Momentum positif
✓ Trader Score tinggi
✓ Market cap rank kuat

CONFIRMATION:
✓ Support resistance
✓ Volume meningkat
✓ Risk reward minimal 1:2

RISK:
- Jangan entry hanya karena trending
- Hindari membeli candle yang sudah terlalu tinggi
- Gunakan stop loss


"""
    )



print("="*65)

Result:

Conclusion

This project successfully develops a MarketFlow AI Crypto Trading Scanner that combines trending asset detection, momentum scoring, visualization, and market sentiment analysis.

The system converts raw cryptocurrency market data into a structured trading intelligence framework. The Trader Score model evaluates short-term momentum based on price movement, market ranking, and trading activity.

The momentum heatmap provides a visual overview of market conditions, while the final trading report summarizes the strongest momentum opportunity and overall market sentiment.

However, this scanner should not be considered a standalone trading system. Additional analysis such as volatility measurement, risk management, liquidity evaluation, technical confirmation, and broader market conditions is required before making trading decisions.

Overall, MarketFlow AI Crypto Trading Scanner demonstrates how automated data processing can support systematic cryptocurrency market monitoring and opportunity screening.