Analytics
August 10, 2023

How Can You Extract Data Insights Using ChatGPT?

OpenAI's ChatGPT stands out due to its advanced language model capabilities. 

ChatGPT is engineered to have the ability to understand context, generate human-like text, and provide nuanced responses. It makes it a powerful ally for analytically-driven performance marketers. AI tools like ChatGPT can enhance the scope of performance marketing by facilitating improved data analysis, content generation, customer interaction, testing, and much more.

How can ChatGPT help with extracting data insights?

  1. Data analysis and interpretation:

    ChatGPT's ability to interpret complex data sets such as website traffic, conversion rates, customer behavior, and sentiment analysis is a game-changer for performance marketers. It can take raw data and help you with: 

    a. Converting data into easily digestible metrics, e.g. ROI, ROAS, CLV, churn rate, etc.
    b. Identifying patterns and trends, say, consumer behavior and campaign performance
    c. Generate reports and charts, by using a plugin like Code Interpreter

    For example, by analyzing data on customer purchases, ChatGPT can pinpoint peak purchasing times. With this information, marketers can optimize the timing of their campaigns to match when their audience is most likely to make a purchase.

    Alternatively, you can also just feed the raw Excel data into the chat interface and ask it to generate insights. Although, there is a character limit so you may not be able to feed very large datasets.

    Here are some more examples of ChatGPT prompts that you can use: 
Can you analyze this data set and summarize the key insights? Excel Data: [Copy-paste the data set here]

Based on the following investment portfolio data, can you summarize the performance of the stocks over the last year? [Enter the data file or upload the data with the Code Interpreter plugin]

Using the given employee satisfaction survey data, can you identify the main areas of dissatisfaction? [Enter the data file or upload the data with the Code Interpreter plugin]

Using the text dataset shared of product reviews, can you perform the below tasks:
- Identify common sentiments expressed by the customers
- Based on the language used in the reviews, categorize the sentiments expressed as strongly positive, positive, neutral, negative, or strongly negative.
- Are there any frequently mentioned suggestions for product improvements or features that customers would like to see added? [Enter the data file or upload the data with the Code Interpreter plugin]

  1. Formulate complex Excel formula for data analysis: Do you struggle to remember the Excel formula that can simplify a gigantic table and help you clean up the data set faster? 

    With ChatGPT, you can formulate ideas based on specific instructions, to create formulae with natural explanations of what each element does. Conversely, it can help with decoding a formula in case you’re stuck and not able to figure out why a particular formula is not working. 
ChatGPT logo
Prompt: I have 2 Excel sheets; one has details about different products, titled "Products" and the other one has details on the sales done, titled "Sales".
Products sheet has the following data: Product ID, Product Name, Unit Price
Sales sheet has the following: Sales ID, Customer ID, Date, Product ID, Quantity Sold
I want to create an invoice in a completely different sheet titled, "Invoice" with details from both these sheets viz, Sales ID, Customer ID, Date of Sale, Product Name, Quantity Sold, Unit Price, and Total Sales Amount.

Is there an Excel formula that will help me populate these details automatically against the Customer ID and generate invoices?
expand_more

ChatGPT response: Yes, you can use Excel formulas and functions to automatically populate the details from the "Products" and "Sales" sheets into the "Invoice" sheet based on the Customer ID. To achieve this, you can use the combination of VLOOKUP or XLOOKUP functions along with SUMPRODUCT or SUMIFS functions, depending on your Excel version. Here's how you can do it:

Assuming your "Products" sheet is in Sheet1, and the "Sales" sheet is in Sheet2, and you want to generate the invoice in a new sheet named "Invoice" (Sheet3), follow these steps:

1. In the "Invoice" sheet, set up the headers for the columns: Sales ID, Customer ID, Date of Sale, Product Name, Quantity Sold, Unit Price, and Total Sales Amount.

2. Under the "Customer ID" column in the "Invoice" sheet, enter the Customer ID for which you want to generate the invoice.

3. In the "Sales ID" column of the "Invoice" sheet, you can use either VLOOKUP or XLOOKUP function (if available in your Excel version) to fetch the Sales ID based on the Customer ID from the "Sales" sheet. For example:

a. For VLOOKUP (if you are using an older Excel version): =VLOOKUP($A2, Sheet2!$B:$E, 1, FALSE)

b. For XLOOKUP (if you are using Excel 365 or later versions): =XLOOKUP($A2, Sheet2!$B:$B, Sheet2!$A:$A)

4. In the "Date of Sale" column of the "Invoice" sheet, use VLOOKUP or XLOOKUP function to fetch the Date of Sale based on the Sales ID from the "Sales" sheet. For example:

a. For VLOOKUP: =VLOOKUP(B2, Sheet2!$B:$E, 2, FALSE)

b. For XLOOKUP: =XLOOKUP(B2, Sheet2!$B:$B, Sheet2!$C:$C)

5. In the "Product Name" column of the "Invoice" sheet, use VLOOKUP or XLOOKUP function to fetch the Product Name based on the Sales ID from the "Sales" sheet. For example:

a. For VLOOKUP: =VLOOKUP(B2, Sheet2!$B:$E, 4, FALSE)

b. For XLOOKUP: =XLOOKUP(B2, Sheet2!$B:$B, Sheet2!$D:$D)

6. In the "Quantity Sold" column of the "Invoice" sheet, use SUMIFS or SUMPRODUCT function to calculate the total quantity sold for each product based on the Customer ID. For example, if your "Sales" sheet starts from row 2, you can use: =SUMIFS(Sheet2!$D:$D, Sheet2!$B:$B, $A2)

7. In the "Unit Price" column of the "Invoice" sheet, use VLOOKUP or XLOOKUP function to fetch the Unit Price based on the Product Name from the "Products" sheet. For example:

a. For VLOOKUP: =VLOOKUP(D2, Sheet1!$B:$C, 2, FALSE)

b. For XLOOKUP: =XLOOKUP(D2, Sheet1!$B:$B, Sheet1!$C:$C)

8. In the "Total Sales Amount" column of the "Invoice" sheet, calculate the total sales amount for each product using the formula: =E2 * F2


Finally, drag the formulas down to fill in the information for all the products sold to that particular customer. The "Invoice" sheet will automatically populate the required details for each customer based on the Customer ID.

Note: Make sure the references to sheet names and column ranges are accurate in the formulas, and adjust them accordingly if your data is in different locations. Also, ensure that the Customer IDs match between the "Sales" and "Products" sheets.

ChatGPT logo
Prompt: How to do the same on Google Sheets?
expand_more

ChatGPT response: You can achieve the same functionality in Google Sheets as well using similar formulas. Google Sheets offers equivalents to many Excel functions, so the transition from Excel to Google Sheets is generally straightforward. Here's how you can populate the details in the "Invoice" sheet based on the Customer ID using Google Sheets:

Assuming your "Products" sheet is in Sheet1, and the "Sales" sheet is in Sheet2, and you want to generate the invoice in a new sheet named "Invoice" (Sheet3), follow these steps:

1. In the "Invoice" sheet, set up the headers for the columns: Sales ID, Customer ID, Date of Sale, Product Name, Quantity Sold, Unit Price, and Total Sales Amount.

2. Under the "Customer ID" column in the "Invoice" sheet, enter the Customer ID for which you want to generate the invoice.

3. In the "Sales ID" column of the "Invoice" sheet, use the VLOOKUP function to fetch the Sales ID based on the Customer ID from the "Sales" sheet. For example: =VLOOKUP($A2, Sheet2!$B$2:$E, 1, FALSE)

4. In the "Date of Sale" column of the "Invoice" sheet, use the VLOOKUP function to fetch the Date of Sale based on the Sales ID from the "Sales" sheet. For example: =VLOOKUP(B2, Sheet2!$B$2:$E, 2, FALSE)

5. In the "Product Name" column of the "Invoice" sheet, use the VLOOKUP function to fetch the Product Name based on the Sales ID from the "Sales" sheet. For example: =VLOOKUP(B2, Sheet2!$B$2:$E, 4, FALSE)

6. In the "Quantity Sold" column of the "Invoice" sheet, use the SUMIF function to calculate the total quantity sold for each product based on the Customer ID. For example: =SUMIF(Sheet2!$B$2:$B, $A2, Sheet2!$D$2:$D)

7. In the "Unit Price" column of the "Invoice" sheet, use the VLOOKUP function to fetch the Unit Price based on the Product Name from the "Products" sheet. For example: =VLOOKUP(D2, Sheet1!$B$2:$C, 2, FALSE)

8. In the "Total Sales Amount" column of the "Invoice" sheet, calculate the total sales amount for each product using the formula: =E2 * F2


Finally, drag the formulas down to fill in the information for all the products sold to that particular customer. The "Invoice" sheet in Google Sheets will automatically populate the required details for each customer based on the Customer ID.

Make sure the references to sheet names and cell ranges are accurate in the formulas, and adjust them accordingly if your data is in different locations. Also, ensure that the Customer IDs match between the "Sales" and "Products" sheets.

  1. Testing and optimization: ChatGPT can also support marketers with testing and optimization efforts. It can analyze results from A/B tests, providing insights on which version performs better and why, and even suggesting improvements for underperforming versions. 

    For example, if the ChatGPT is provided with the results of the A/B test for ad copy, it can highlight which ad copy performed better and provide insights on why it was more successful, helping marketers refine their strategies.

    Let’s see an example of the insights it can provide on email subject lines and even share optimized options: 

ChatGPT logo
Prompt: Below are a few subject lines that we are considering for the upcoming sale of flight tickets. Could you share your insights on which would perform better? Also, can you suggest alternative subject lines that would work better: 
1. "Don't Miss Out! Exclusive Flight Deals Inside" 
2. "Limited Time Offer: Affordable Flights Await You!" 
3. "Unleash Your Wanderlust with Our Special Flight Deals" 
4. "Take to the Skies: Unbeatable Prices on Flights"
expand_more

ChatGPT response: These are all strong subject lines, but each could perform differently depending on your specific audience's preferences and behaviors. Here are some thoughts on each:
1. "Don't Miss Out! Exclusive Flight Deals Inside": This subject line creates a sense of urgency and exclusivity which can be powerful motivators. However, the term "Don't Miss Out" is often overused and might not stand out in a crowded inbox.
2. "Limited Time Offer: Affordable Flights Await You!": The "Limited Time Offer" emphasizes urgency, which could prompt immediate action. The mention of "Affordable Flights" might appeal to cost-conscious customers.
3. "Unleash Your Wanderlust with Our Special Flight Deals": This subject line appeals to emotions and the desire for travel, which might resonate with your audience, especially if they are travel enthusiasts.
4. "Take to the Skies: Unbeatable Prices on Flights": This subject line combines the excitement of travel ("Take to the Skies") with a value proposition ("Unbeatable Prices"), which could be a powerful combination.

Here are some alternative subject lines with a festive twist:
1. "Celebrate the Season with Exclusive Flight Discounts!"
2. "Festive Flight Sale: Travel More, Spend Less!"
3. "Your Festive Travel Begins Here - Unbeatable Flight Deals!"
4. "Seasonal Savings: Unwrap Exclusive Flight Offers!"
5. "Deck the Skies: Special Flight Deals Just For You!"

Remember, the effectiveness of email subject lines can be highly dependent on the specific preferences of your audience. It would be best to use A/B testing to try out different subject lines and see which ones achieve the highest open and click-through rates.

  1. Keyword performance: You can use ChatGPT to analyze the performance of different keywords used in the ad campaigns. You can use it to identify keywords that hit your ROA targets, as well as identify negative keywords that may be hurting your campaign performance.

    Conversely, you can even use a prompt like the example below to help analyze keywords and optimize your email or ad campaign:
Could you evaluate the effectiveness of my ad campaign? Here is a dataset containing the ad titles, keywords, impressions, clicks, click-through rates (CTR), conversion rates, cost per click (CPC), and cost per conversion for each ad.

Using this data, can you indicate which ads were successful in driving conversions at the lowest cost per conversion as well as point out any ads that might be negatively impacting my overall campaign performance? Furthermore, could you offer insights on how I can optimize the content and timing of each ad to enhance the overall performance of my campaign?

Here is the dataset: [plug in data from CSV file or use code interpreter plugin to upload and read the file]

Based on your analysis, please also recommend new ad titles and keywords that are worth testing.

  1. Competitor analysis: ChatGPT plugin Competitor PPC Ads plugin can help with analyzing your competitor’s PPC campaigns. It provides insights on what keywords competitors are targeting; what kind of content they're producing, and how they're interacting with their customers.

    Here are some prompts examples that you can use:
Can you use the Competitor PPC plugin to find the ads on: [site URL]

I want to see the PPC ad history for the website: [site URL]

Use the Competitor PPC plugin to retrieve the latest ads for: [site URL]

Can you show me the PPC ads of my competitor: [site URL]

With the insights that you receive, you can choose from the following:

  • Conduct further data analysis and research to identify your USPs, key messaging, and optimize the ads with A/B testing. 
  • Ask ChatGPT to create similar ads for your brand/product/service and then edit them as per your requirement. 

    Do remember that the goal here is not to copy from competitors but learn from them, and craft a campaign that is more effective and impactful.  

  1. Forecasting and predictive analysis: Because of its large data processing ability and predictive analysis, ChatGPT can predict how changes in strategy could impact key metrics like customer acquisition costs, conversion rates, or customer lifetime value. 

Let’s explore this in 3 different use cases:

Case - 1: Using Code Interpreter Plugin

Due to its limitations, ChatGPT alone cannot read large data files and build models, but with the Code Interpreter plugin, it is possible. 

With this plugin, ChatGPT can access Python’s data visualization libraries and create charts and plots such as line plots, bar charts, scatter plots, heatmaps, histograms, and pie charts. You just need to type in the right Python code to create relevant charts. 

Here is the flow that you can follow: 

  1. Activate Code Interpreter Plugin from Settings > Beta Features on your ChatGPT Plus account. And select it on your GPT-4 chat interface as well before starting the conversation.

  1. You can start the conversation with it by asking if it can perform forecasting.

    Example prompt: Hi, I have a time series data of monthly ad campaign performance for my company spanning the last 5 years. I need help in forecasting ad performance for the next 2 months.
  2. It would prompt you to upload the file which you can do so by using Code Interpreter. 
  3. As it reads the data, it might suggest a forecasting model to use. Or you can even prompt it to suggest which model would suit the best for the desired result. 
  4. Based on your interactions with it, and the command you give, ChatGPT will be able to give you forecasted results.

Case - 2: Using ChatGPT to interpret forecasting results

If you are using other data visualization tools and unable to interpret results from them, then you can take ChatGPT’s help in interpreting results. You can do it by a prompt like:

Here's the output of my ARIMA model for sales forecasting. Can you help me interpret the results?

Case - 3: If you do not have a ChatGPT Plus account or can’t access Code Interpreter Plugin

You need a ChatGPT Plus account to access the plugin and run advanced statistical models or machine learning algorithms. 

In case you don’t have the Plus account or for some reason are unable to access Code Interpreter, ChatGPT can help you with explaining how different predictive models work; which models would be appropriate to use for the results you want, or even interpret the results for you. 

Have a look at these example prompts:

What type of forecasting model would be best suited for predicting future sales based on this historical sales data?

Given the following website traffic data, what can we infer about future traffic trends?

What are some common methods for financial forecasting?

What factors should I consider when forecasting demand for a new product?

From providing customer engagement insights to personalizing content to analyzing vast troves of data for actionable insights, ChatGPT can provide a range of benefits bolstering marketing strategies and outcomes.

As we look ahead, one thing is clear - AI is not just a fleeting trend in marketing. With AI, you can assign all the mundane tasks to it while you spend more time on strategic tasks or making decisions. 

Have you started using ChatGPT in your performance marketing strategies? Let us know about your experience here.

Want to cut the clutter and get information directly in your mailbox?