亚马逊运营 AI 应用：10个必做事项提升跨境电商效率

import requests
import pandas as pd
from datetime import datetime

class AmazonAIAnalyzer:
    def __init__(self, api_key):
        self.api_key = api_key
        self.base_url = "https://api.pangolinfo.com/v1"
        
    def get_category_data(self, category_id, country="US"):
        """获取类目数据"""
        headers = {"Authorization": f"Bearer {self.api_key}"}
        params = {
            "category_id": category_id,
            "country": country,
            "limit": 100,
            "sort_by": "sales_rank"
        }
        
        response = requests.get(
            f"{self.base_url}/amazon/category",
            headers=headers,
            params=params
        )
        
        if response.status_code == 200:
            return response.json()["data"]
        else:
            raise Exception(f"API请求失败: {response.status_code}")
    
    def analyze_market_opportunity(self, products_data):
        """分析市场机会"""
        df = pd.DataFrame(products_data)
        
        # 计算关键指标
        df["review_velocity"] = df["reviews_count"] / df["days_since_launch"]
        df["price_competitiveness"] = df["price"] / df["category_avg_price"]
        df["demand_score"] = df["sales_rank"].apply(
            lambda x: 100 / (1 + x/1000) if x > 0 else 0
        )
        
        # 识别蓝海机会
        blue_ocean_criteria = (
            (df["review_velocity"] > 0.5) &  # 评论增长快
            (df["price_competitiveness"] < 0.8) &  # 价格有优势
            (df["demand_score"] > 60) &  # 需求旺盛
            (df["competition_score"] < 40)  # 竞争度低
        )
        
        opportunities = df[blue_ocean_criteria].sort_values(
            "demand_score", ascending=False
        )
        
        return opportunities.to_dict("records")
    
    def generate_product_recommendations(self, opportunities):
        """生成产品推荐"""
        recommendations = []
        
        for opp in opportunities[:5]:  # 取前5个机会
            recommendation = {
                "asin": opp["asin"],
                "title": opp["title"],
                "estimated_monthly_sales": opp["estimated_sales"],
                "estimated_profit_margin": self.calculate_profit_margin(opp),
                "competition_level": self.assess_competition(opp),
                "investment_required": self.estimate_investment(opp),
                "risk_level": self.assess_risk(opp)
            }
            recommendations.append(recommendation)
        
        return recommendations
    
    def calculate_profit_margin(self, product_data):
        """计算利润率"""
        # 简化计算：假设成本为价格的40%
        cost = product_data["price"] * 0.4
        profit = product_data["price"] - cost
        return round(profit / product_data["price"] * 100, 1)
    
    def assess_competition(self, product_data):
        """评估竞争程度"""
        review_count = product_data["reviews_count"]
        rating = product_data["rating"]
        
        if review_count < 50 and rating < 4.0:
            return "低"
        elif review_count < 200 and rating < 4.5:
            return "中"
        else:
            return "高"
    
    def estimate_investment(self, product_data):
        """估算投资需求"""
        # 包括库存、广告、运营等成本
        monthly_sales = product_data["estimated_sales"]
        price = product_data["price"]
        
        inventory_cost = monthly_sales * price * 0.6  # 60%库存成本
        advertising_cost = monthly_sales * price * 0.15  # 15%广告预算
        operational_cost = monthly_sales * price * 0.1  # 10%运营成本
        
        return round(inventory_cost + advertising_cost + operational_cost, 2)
    
    def assess_risk(self, product_data):
        """评估风险等级"""
        factors = {
            "seasonality": self.check_seasonality(product_data),
            "brand_dominance": self.check_brand_dominance(product_data),
            "technology_dependency": self.check_tech_dependency(product_data)
        }
        
        risk_score = sum(factors.values()) / len(factors)
        
        if risk_score < 0.3:
            return "低风险"
        elif risk_score < 0.6:
            return "中风险"
        else:
            return "高风险"

# 使用示例
if __name__ == "__main__":
    analyzer = AmazonAIAnalyzer(api_key="your_pangolinfo_api_key")
    
    # 获取家居类目数据
    home_category_data = analyzer.get_category_data("1055398", "US")
    
    # 分析市场机会
    opportunities = analyzer.analyze_market_opportunity(home_category_data)
    
    # 生成产品推荐
    recommendations = analyzer.generate_product_recommendations(opportunities)
    
    print(f"发现 {len(opportunities)} 个市场机会")
    print("Top 5 产品推荐:")
    for i, rec in enumerate(recommendations, 1):
        print(f"{i}. {rec['title']}")
        print(f"   预估月销量: {rec['estimated_monthly_sales']}")
        print(f"   预估利润率: {rec['estimated_profit_margin']}%")
        print(f"   竞争程度: {rec['competition_level']}")
        print(f"   投资需求: ${rec['investment_required']}")
        print(f"   风险等级: {rec['risk_level']}")
        print()