AI-фандрайзинг для НКО: персоналізація звернень і прогнозування

import numpy as np
import pandas as pd
from sklearn.ensemble import GradientBoostingClassifier
from anthropic import Anthropic
import json

class DonorPropensityModel:
    """Предсказание вероятности следующего пожертвования"""
    def __init__(self):
        self.model = GradientBoostingClassifier(
            n_estimators=200,
            learning_rate=0.05,
            max_depth=4,
            random_state=42
        )

    def build_rfm_features(self, donor_history: pd.DataFrame) -> pd.DataFrame:
        """RFM + дополнительные признаки для фандрайзинга"""
        today = pd.Timestamp.now()
        donor_stats = donor_history.groupby('donor_id').agg(
            recency=('donation_date', lambda x: (today - x.max()).days),
            frequency=('donation_id', 'count'),
            monetary=('amount', 'sum'),
            avg_donation=('amount', 'mean'),
            last_amount=('amount', 'last'),
            max_donation=('amount', 'max'),
            first_donation_days=('donation_date', lambda x: (today - x.min()).days),
        ).reset_index()

        # Тренд: растут ли суммы?
        def donation_trend(group):
            if len(group) < 3:
                return 0
            x = np.arange(len(group))
            y = group['amount'].values
            return np.polyfit(x, y, 1)[0]  # Slope

        trends = donor_history.groupby('donor_id').apply(donation_trend)
        donor_stats['donation_trend'] = donor_stats['donor_id'].map(trends).fillna(0)

        # Сезонность: давал ли в конце года (высокий сезон для НКО)?
        year_end = donor_history[donor_history['donation_date'].dt.month.isin([11, 12])]
        year_end_donors = set(year_end['donor_id'])
        donor_stats['gives_year_end'] = donor_stats['donor_id'].isin(year_end_donors).astype(int)

        return donor_stats

    def predict_next_gift(self, donors: pd.DataFrame) -> pd.DataFrame:
        """Скоринг вероятности следующего пожертвования (90 дней)"""
        features = self.build_rfm_features(donors)
        feature_cols = ['recency', 'frequency', 'monetary', 'avg_donation', 'donation_trend', 'gives_year_end']
        X = features[feature_cols].fillna(0)
        probs = self.model.predict_proba(X)[:, 1]
        features['propensity_score'] = probs
        features['ask_amount'] = self._suggest_ask_amount(features)
        features['donor_tier'] = pd.cut(
            probs,
            bins=[0, 0.2, 0.5, 0.75, 1.0],
            labels=['lapsed', 'occasional', 'regular', 'loyal']
        )
        return features

    def _suggest_ask_amount(self, donors: pd.DataFrame) -> pd.Series:
        """Предлагаемая сумма запроса: слегка выше средней"""
        return (donors['avg_donation'] * 1.2).round(-1)  # Округляем до десятков

class PersonalizedDonorOutreach:
    """Персонализированные обращения к донорам"""
    def __init__(self):
        self.llm = Anthropic()

    def generate_appeal(self, donor: dict, campaign: dict, ask_amount: float) -> dict:
        """Персонализированное письмо для донора"""
        response = self.llm.messages.create(
            model="claude-3-5-sonnet-20241022",
            max_tokens=350,
            messages=[{
                "role": "user",
                "content": f"""Write a personalized fundraising appeal in Russian.
Donor profile:
- Name: {donor.get('first_name', 'Друг')}
- Giving history: {donor.get('frequency', 1)} gifts, average ${donor.get('avg_donation', 50):.0f}
- Last gift: {donor.get('last_amount', 50)} {donor.get('recency', 30)} days ago
- Main interests: {donor.get('cause_interests', ['general support'])}
Campaign: {campaign.get('name')}
Campaign story: {campaign.get('impact_story', '')[:200]}
Ask amount: ${ask_amount:.0f}
Write:
1. Personal opening (acknowledge their history)
2. Impact story (specific, emotional)
3. Clear ask with specific amount and its impact
4. Warm closing
Max 200 words. No generic phrases."""
            }]
        )
        subject_response = self.llm.messages.create(
            model="claude-3-5-sonnet-20241022",
            max_tokens=50,
            messages=[{
                "role": "user",
                "content": f"Write a compelling email subject line in Russian for this fundraising appeal. Max 50 chars. Campaign: {campaign.get('name')}. Donor's interests: {donor.get('cause_interests', [])}."
            }]
        )
        return {
            'subject': subject_response.content[0].text.strip(),
            'body': response.content[0].text,
            'ask_amount': ask_amount,
            'donor_id': donor.get('id')
        }

    def determine_best_channel(self, donor: dict) -> str:
        """Канал коммуникации на основе истории отклика"""
        response_rates = donor.get('channel_response_rates', {})
        if not response_rates:
            return 'email'
        return max(response_rates, key=response_rates.get)