GPT-4o Laziness is not a crime

🔹GPT-4o related videos:
• GPT-4o 房地產與現住人口數分析
• GPT-4o 理解和處理圖像(上) #ai...
• GPT-4o 理解和處理圖像(下) #ai...
• GPT-4o 一道指令輕鬆完成專業的銷售分析...
• GPT-4o 進行北北基桃空氣品質分析 | ...
• GPT-4o 輕鬆上手資料分析 | 鐵達尼號...
• 全網最詳細 | GPT-4o 能力探索 | ...
• 解決 GPT-4o | 圖表中文字亂碼問題？...
• OpenAI GPT-4o 革命性的AI模型...
• GPT-4o 進行台北房地產分析 | 感謝頻...
• GPT-4o 零代碼銷售數據分析 | 提供資...
• GPT-4o 這樣用才專業：公司財報分析 |...
🔹Joining the advanced membership is the quickest way: / @changlunglung
🔹Small sponsorship for Dragon AI and programming combat
-------------------------------------------------
🎉Method one: Join the channel membership (After joining, you can watch videos in the member area): / @changlunglung
🎉Method two: Click the "Super Thanks" button in the bottom right corner of the RUclips video.
🎉Method three (buy Long Long coffee): buymeacoffee.com/changlunglung
-------------------------------------------------
🔹Strongly recommended, courses to enhance your workplace competitiveness, co-operated by Long Long and Master Computer:
Rely on ChatGPT's comprehensive workplace scenario application for the golden decade in the workplace (Reserve your dreams): www.worker360.com.tw/video/Di...
Even with zero foundation: Quickly learn to build your own enterprise-level speech-to-text service! (Order now): www.worker360.com.tw/video/Di...
🔹dataset download:
www.kaggle.com/datasets/carri...
🔹First section prompt:
All responses thereafter will be provided and displayed in English. Then, follow the instructions below to complete the task. If there's anything that needs confirmation during the process, proceed with your suggested solution without asking me again. To avoid an overly long information, each major task will be executed separately. Move on to the next task in a new window after completing the current one.
First: Start by cleaning the dataset and inform me of any issues with the data along with proposed solutions.
Second: Conduct sales trend analysis to understand changes in sales revenue and volume. Use time series analysis, data visualization, and statistical methods to reveal seasonal variations and long-term trends.
Third: Analyze the sales performance of different products to understand sales revenue, inventory, and profitability for each product. Analyze by product category, sales channel, and sales region to identify the best-selling products and those with the highest growth potential.
Fourth: I want to analyze customer purchasing behavior and loyalty to understand customer value and behavior patterns. Please conduct customer segmentation, RFM (Recency, Frequency, Monetary) analysis, and forecast sales for the next six months to improve customer experience and personalized marketing.
Fifth: Finally, please generate a report with graphs, tables, and text based on the above analyses or insights. The report is intended for the chairman and should help the business team evaluate the effectiveness of sales strategies and activities, and enable continuous optimization and adjustment.
🔹Final section, sales forecast prompt:
Please use the machine learning method Support Vector Machine (SVM) to predict future sales.
Support Vector Machine (SVM) is a supervised learning model commonly used for classification problems, but it can also be applied to regression analysis, in which case it is referred to as Support Vector Regression (SVR). It is suitable for predicting nonlinear and high-dimensional data.
However, it's important to note that SVR, like most machine learning models, does not directly handle the time dependency of time series data. This means that we need to create some features (such as past sales data, seasonal indicators, etc.) to capture this dependency.
Here, I will use the following steps to build and train the SVR model:
1.Feature Creation: Create new features based on past sales data and timestamp information (such as year, month, season, etc.).
2.Data Splitting: Divide the dataset into training and testing sets.
3.Data Standardization: Scale the features to the same range to improve model performance.
4.Model Training: Train the SVR model using the training data and corresponding target values (i.e., sales data).
5.Model Validation: Evaluate the performance of the model using the testing data.
6.Future Prediction: Use the model to predict future sales data.