Прогноз повторных покупок и маркетинговые стратегии для розницы

Дом

Список AI-промптов

Инструмент прогноза повторных покупок клиентов

${:__('collect %s',Инструмент прогноза повторных покупок клиентов)}$

Обрабатывает исторические данные о покупках клиентов розницы, прогнозирует вероятность повторной покупки за 3 месяца, отбирает перспективных клиентов и составляет персональные маркетинговые планы.

Содержание промпта

Копировать

Process 12 months of customer consumption records from a offline chain convenience store, calculate each customer's consumption interval, average order value and total consumption times features, predict each customer's repurchase probability in the next three months, screen dormant customers with repurchase probability over 60%, match each selected customer with a matching discount coupon outreach plan that fits their consumption preference, and organize the result into a clear executable table.

Копировать

Обработайте записи о покупках клиентов за 12 месяцев от сетевого офлайн-магазина, рассчитайте для каждого клиента характеристики: интервал между покупками, средний чек и общее количество покупок, спрогнозируйте вероятность повторной покупки каждого клиента в ближайшие три месяца, отберите спящих клиентов с вероятностью повторной покупки выше 60%, подберите для каждого отобранного клиента программу распространения скидочных купонов, соответствующую его предпочтениям в покупках, и оформите результат в понятную готовую таблицу.

Копировать

Поделиться Нажмите, чтобы скопировать ссылку

Комментарии (1)

0/300

Представлять на рассмотрение

BenHernández

13 октября 2026 г., 23:26:34 GMT+03:00

コンビニの購買データ1年間を分析して再購入確率を予測するツール、なかなか実用的だな。休眠顧客に適切なクーポンを送るって発想は良いけど、オフライン店舗のデータ収集が面倒そう。でも、実行可能なテーブルに出力されるなら業務効率化に役立ちそう。試してみよう！

Рекомендация

Классификация тикетов EC

Please analyze the following user customer service conversation records from an e-commerce platform, determine the business category based on the content such as logistics inquiry, return or exchange application, product quality complaint, or account anomaly, extract key information like order number, problem description, and user sentiment, and finally output a structured ticket classification result for subsequent manual or automated processing.

Классификация тикетов EC

Please analyze the content of the following user customer service tickets from an e-commerce platform, determine which category their core request belongs to based on the conversation context (logistics inquiry, return/exchange application, product quality complaint, or price consultation), and output the corresponding category label along with a brief reason.

Классификация Тикетов

Analyze the following e-commerce support ticket content, identify its core issue type, including logistics delay, product damage, refund request, or inquiry, and route it to the logistics, quality inspection, or finance department based on preset rules. Extract key entities such as order number, product name, and user sentiment, and finally output a structured classification result and suggested handling plan to ensure accurate classification and compliance with business standards.

Классификатор тикетов e-commerce

Act as an intelligent customer service system for an e-commerce platform. Receive raw user inquiry or complaint text, analyze its core intent, and classify it into specific business scenarios such as logistics inquiry, product quality issue, return or exchange request, or price dispute. Output a standardized classification label along with a brief handling suggestion to ensure the customer service team can respond quickly and accurately.

Классификация Тикетов

Please analyze the following e-commerce customer inquiry ticket content, automatically categorize it into one of the four categories: 'Logistics Inquiry', 'Return/Exchange Application', 'Product Quality Complaint', or 'Other Inquiry' based on business semantics, and briefly explain the basis for classification, ensuring that the classification results conform to actual business scenarios and are logically clear.

Классификатор тикетов E-commerce

Act as an e-commerce support specialist to analyze the provided customer ticket text, identifying whether the core issue falls under logistics delay, product damage, return/exchange request, or price dispute. Extract key entities such as order ID, product name, and user sentiment, then output a structured classification result with suggested handling priority, ensuring accuracy and compliance with company service standards.