Prepare your data for import to hila

As a specific use case, for an FP&A individual in a CFO’s office, hila’s Conversational Finance provides timely, accurate information with charts, tables and analysis on ERP systems. With Vianai’s specialized models and anti-hallucination features, the responses back from a system of record are 100 percent accurate and occur after asking a simple question. There is no need to send the question to a business analyst, an IT department or specialist for further analysis.

Preparing your data for Conversational Finance involves two steps:

• Prepare the data (customer task)
• Configure hila to ingest the data (Professional Services or client IT task)

Prepare the data

For the current release, you need to prepare the data for Conversational Finance in the form of CSV or parquet files that you give to your Professional Services or client IT contact for the next step.

To set up and populate Conversational Finance with pilot data for your organization, you need to prepare and provide the data in a standard format. You can do this by running a custom report in your financial system and exporting the data to a CSV file with expected columns and data. Or you can export data from your financial system in an Excel file and then transform this data to this standard format.

The core Conversational Finance flat tables contain the columns listed in the following image:

Example files

Each table below has an example CSV file you can read to make sure your files are in the right format.

Following is a link to download example files in parquet format that you can load into hila Conversational Finance and ask questions against.

Example files

Journal table

Journal table contains transaction data from your general ledger in a flat de-normalized format. The following columns are available in the journal table:

Template for journal data: journal_template.csv

Sample journal data: journal.csv

Comments:

• fiscal_year, fiscal_quarter, fiscal_month and fiscal_period columns are populated automatically from the fiscal_calendar table or generated using posting_date automatically if fiscal calendar is aligned with calendar year.
• account_name, account_type and account_category columns are populated from account table.
• Most of the columns have been marked as not required. However, capabilities and diversity of questions that can be asked are directly dependent on data availability in all or most of these columns.
• For each reference field like department, cost center, profit center, supplier, etc., both number and name columns are provided. You can provide either number or name or both. However, providing both will help you filter data using either number or name. You may join with your reference tables to populate these fields in flattened journal table. For simplicity, Conversational Finance does not expect master data tables for each of these fields to be populated.

Account table

Account table contains general ledger account information. The following columns must be populated in this table for each of the accounts that appear in the journal table:

Template for account data: account_template.csv

Sample account data: account.csv

Comments:

• account_type column is used to categorize accounts into different types like Revenue and Expense.
• account_category column is used to categorize accounts into different categories like Cost of Goods Sold, Operating Expenses, etc.

Fiscal calendar table

If your organization follows a fiscal year calendar that is aligned with a calendar year, then you just need to provide the start date of the fiscal year. For example, if your fiscal year starts on 1st January, the fiscal year and calendar year are expected to be identical. If your fiscal year starts on 1st of July for example, then Q1 of the fiscal year would be 1st July to 30th September, Q2 would be 1st October to 31st December, and so on. In such cases, Professional Services will be able to generate a fiscal calendar table for queries automatically. However, if your organization follows a non-standard fiscal year calendar, you will need to provide a fiscal_calendar.parquet file.

Template for fiscal calendar data: fiscal_calendar_template.csv

Sample fiscal calendar data: fiscal_calendar.csv

Comments:

• If your organization follows a fiscal year calendar that is aligned with a calendar year, then you just need to provide the start date of the fiscal year.

Company table

Company provides details about your company or companies.

Template for company data: company_template.csv

Sample company data: company.csv

Configure hila

After you have prepared the data, convert your CSV files to parquet and send the data to your Professional Services or client IT contact. They will configure hila to ingest the data and set up Conversational Finance for your organization.