Legal teams spend immense amounts of time dealing with the same requests over and over again. At the same time, it's vital to provide timely responses to preserve client relationships.
Failing to quickly provide accurate legal responses can have serious repercussions. For instance, the GDPR Data Protection Act mandates that data controllers have up to 30 days to respond to a Subject Access Request, or SAR. Violations of the GDPR, including this clause, lead to penalties of up to 4% of a company’s total global turnover.
This can have serious financial consequences for organizations, so it's crucial that legal teams are well prepared. It goes far beyond GDPR, and many legal letters contain a date for you to reply by. For example, a cease and desist letter will commonly have a time to reply by, such as 7 days, while failure to respond to copyright infringement notices may result in a lawsuit.
In the financial world, consumer legal complaints are often submitted through the Consumer Financial Protection Bureau, which typically requires a financial company to respond to the consumer within 15 days of a complaint.
Failure to respond to legal letters can lead to dire consequences for your company. So, what can you do to ensure that all legal letters are responded to correctly and effectively? Akkio can automatically parse requests to formulate a relevant response, freeing up your team to focus on more important work.
To get started, simply sign up to Akkio for free. As with any machine learning task, the first step is getting historical data and picking a column to predict.
For demonstration purposes, we’ll be using the Consumer Complaints Dataset for NLP dataset from Kaggle. This dataset consists of a year's worth of consumer complaints, where each row is tagged with a financial product class: Credit reporting, debt collection, mortgages and loans, credit cards, or retail banking.
There are 162,400 consumer submissions with text narratives, which means that we have plenty of data to train a text classification model that will predict the type of complaint. This is useful because legal teams could then automatically send a preliminary email containing relevant resources and links, as well as route the email to the proper team, if needed.
We get starting by creating a new flow, and hitting “Table.” We then upload the CSV.
After the dataset is connected, Akkio will automatically figure out the data types for each column, and also show some basic details, including the number of rows and columns. You’ll also see a scrollable preview of the dataset.
Next, we click on the second step in the AI flow, which is “Predict.” Under “predict fields,” you can select the column to predict, named “Rating.” Then just hit “Create Predictive Model,” and you’re done. In our example below, we achieve close to 80% accuracy from just one column of text input.
Once the model is created, you can get a quick overview of your new predictive model.
When you click “See Model Report,” it will open up a new tab in your browser with an interactive report which allows you to quickly understand what was predicted for each field.
The model report will highlight the following:
You’ll be able to see specific details like the accuracy, model type selected (in this case, Deep Neural Network with Attention was used), and so on. The best way to improve model accuracy is to get additional, high-quality training data. With Akkio, you can easily merge on a new dataset, such as with another source of feedback data.
You can also try increasing training time, which may help increase accuracy, particularly if you have a large dataset to begin with.
Now that we have our classification model trained on some historical data, let’s deploy it. The final step in the flow is to select where your prediction should be made.
In this example above, we’ve built a model to predict the class of a consumer financial complaint, but we could just as easily build a model and deploy it on inbound legal emails, documents, or really any other text source.
With Akkio, we can easily deploy in a variety of settings, including Salesforce, Snowflake, HubSpot, Google Sheets, and more. We can also make fully custom integrations with the API, or use the no-code automation tool Zapier to integrate with thousands of other applications.
For example, we can use Zapier to read inbound emails, send the text to our classification model, and send an email depending on the predicted class. For instance, if the complaint relates to debt collection, then the firm might send resources related to their debt collection terms and conditions, and ask for the user’s patience for a human reply.
With Akkio, teams can scale globally without needing to build or maintain any code or infrastructure themselves. As a result, deployments take moments instead of weeks or months like other machine learning platforms.
Legal responses can be a tremendous resource drain for organizations big and small. Automating responses will decrease time-to-response, route resources more efficiently, and create more productive teams.