DataForest FAQ

DataForest is an AI data analysis desktop app for individuals and small teams. Work from your own questions to process data, run machine learning, build visualizations and create reports, turning scattered data into results you can understand, review and use.

Yes. If you have data but do not know where to begin, or spend too much time preparing spreadsheets, writing analysis code and making reports, describe your goal in natural language and let AI help with the analysis. Explain what the data means and check that the methods and conclusions fit the situation.

Students, teachers and researchers can organize survey, experimental and teaching data. Ecommerce and startup teams can analyze sales, costs and operations. Creators and YouTubers can explore content performance and audience feedback. Individual investors can organize historical market and public financial data to support their own research.

DataForest lowers the barrier to data preparation, exploration, charts and reports for individuals and small teams. AI provides professional analysis capabilities to help you understand data, identify problems and support decisions, improving work and study efficiency. See the pricing page for plans and usage conditions.

DataForest organizes ongoing analysis tasks in one workspace, bringing together data processing, execution, charts and reports so you can review both the process and results. Its local code environment supports long-running machine learning tasks, sustained computation and repeated analysis with a reviewable record.

DataForest supports multiple data formats, including Excel, CSV, TSV, JSON, Parquet, XML and Pickle, as well as Word and TXT text sources. You can organize, analyze and combine information from these files. More data sources, including database connections, are planned for future releases.

Yes. Run classification, clustering and time-series forecasting with built-in data tools such as pandas, NumPy and scikit-learn. Choose methods that fit your question and data, and review model performance, errors and limits. Predictions are uncertain; model output is not a guarantee of future events.

Yes. Visualize your results and create PPT, Word, PDF and Excel deliverables for coursework, research, content creation or team discussions. Before sharing, check that chart definitions, sources and report conclusions agree.

DataForest includes web tools that let AI search for information online. Combine public sources with your own data for organization, comparison and report creation.

DataForest emphasizes reviewable analysis. AI creates a plan for each task, documents evidence for questions and insights, and makes output files, code and content available for inspection. This helps you check conclusions and spot AI hallucinations.

If you value professional analysis, visual feedback and transparent code, DataForest includes Python and a dedicated environment for data analysis and machine learning, including classification, attribution analysis and time-series forecasting.

What is sent to an external model depends on your configuration. You configure the model and can choose a trusted provider or a locally running model API. Local storage and computation are separate from model requests; check the request contents and the provider's data policy. DataForest's three file safeguards prevent the AI agent from directly modifying source files, make real local paths difficult for the model to read, and prevent direct file operations outside the project's output directory.

Training use depends on the model provider's policy and your settings. You configure the model and can choose a trusted provider or a locally running model API. DataForest never obtains your local data or collects it for model training. When using an external model, check the provider's training use, retention and privacy settings.