BASEQ AI is positioned as a no-code platform for business units and a low-code platform for those with technical know-how, a tool that makes it incredibly easy to do faster, better and less costly.

When building and using AI for business use cases, BASEQ positions AI modelling with no-code use. No-code AI effectively uses machine learning (ML) and artificial intelligence (AI) without writing a single line of code. On the No-Code AI platform, users are only expected to upload their data and click a few buttons to get the results.

Everyone from entry-level business analysts to expert data scientists can easily harness the power of machine learning and AI with AI’s No-code AI and intervene at the code level.

Basic requirements:

For example, “Google, Apple, Facebook” are 3 separate values ​​but are treated as a single value.

Personally Identifiable Information (PII) columns (e.g. phone, email, address, etc.) are not required.

You can create a practical data set by categorising long sentences with separate values.

Intermediate requirements

The requirements in the following items are the actions that should be taken for missing data to make your model more efficient.

Missing Data

Advanced requirements

Technical knowledge is recommended for advanced requirements.

Data Enrichment

Create new columns:

The quality of a dataset is often enhanced by deriving new columns from existing columns or by correlating different datasets.

For example, deriving age from date of birth, duration from start and end dates of customer subscription or employment period, etc.

Once new columns are created, unnecessary columns should not be considered for training the data as they are unnecessary information

Additional columns should be created from comma separated values. Columns with values ​​in comma separated format are treated as one long piece of text instead of different values

For example, “Google, Apple, Facebook” are 3 separate values ​​but treated as a single value

Separate columns can be created for each value and filled with 0/1 depending on their existence for a particular row

A predictive question is a question you define when building a BASEQ model expressing the predicted output you expect to extract from the data set.

This question will vary depending on the business problem you want to solve.

For example, “What is the probability that customer segment [ABC] will experience [churn] (a specific activity) in [Q3 2025] (a specific period)?”.

The predictive question guides the model in learning from your data and making predictions.

BASEQ is derived from the words “Base Query” and is addressed to enable all users with basic knowledge and technical knowledge/skills to quickly interpret data sets with the support of Artificial Intelligence and provide all the outputs and visualisations they need.

1. “Quick” mode:
   • The ideal approach for iterating your queries and training set.
   • It allows quick browsing to see how different data elements affect accuracy.
   • While this training method works faster, it may not produce the best possible accuracy.
2. “Precise” Production quality mode:
   • Used to train the production version of your model.
   • It provides more granular control over the training process.
   • Training will be slower but will produce the best possible accuracy.

It is usually recommended that you start with the “Quick” mode and retrain in production mode if the results are satisfactory.

Connecting to different applications and solutions and importing your data is as easy as uploading a file like CSV.

The in-app navigation and controls allow you to connect the application and select data quickly.

To create a predictive ML model, you can briefly follow these steps:

Prepare your Core Set.

Ask your question if you know your data

Baseq will make sense of your data by selecting the most efficient model.

This process is designed for both business units and professional data scientists. It will help you build a great model and generate reports using BASEQ’s unique features.

In general, since machine learning is all about extracting patterns from uploaded datasets, the breadth and quality of the dataset will affect the output. There is technically no limit to the amount of data you can link to your account, but it is limited by your membership features. We recommend that you have at least 1000 rows and 5 columns for your dataset.

BASEQ AI allows the inclusion of different data sources for forecasting datasets. The most well-known and used of these is CSV. You can directly upload a CSV file up to 25 MB to the platform.

Another popular data storage format is Google Spreadsheets. You can upload a Google workbook with multiple sheets to BASEQ AI.

After selection, all file controls will be shown to you, and you will be guided.

With your existing data, you can interpret the past and predict the near future. Getting results with converging ratios about the future makes it easier for you to review your workflows or strategies and work to get closer to your goals.

For example, You can predict your Q4 sales figures by enriching your 2023-2024 sales figures and different data types, and you can determine which channels will increase.

BASEQ AI enables users to make text-based queries with Generative AI capabilities by uploading data sets or taking them with application integrations. The data is then interpreted and visualised by the models according to the expected needs of the queries.

All these steps work only text-based without knowing query languages.

Dataset prerequisites are different, depending on whether AutoML (classification, regression) or Time Series.

In BASEQ AI, it is really easy to load data into your account. In a few clicks, the data set loading is complete. The prerequisites are shown on the screen when the data set shape is selected, and guidance is provided.

BASEQ AI has started to be developed to improve the processes of individual and corporate customers, with the aim of improving customer processes in different scenarios.

When it was developed, it focused on data interpretation and visualization, and R&D processes are ongoing for other scenarios.