Lokad news - Integrated business forecasting

Due to popular demand, we have started to work on Lokad Safety Stock Calculator an analytics application that will be dedicated to inventory optimization.

Soon after the initial release of Lokad Desktop Sales Forecasting, it did become clear that both retailers and manufacturers were needing a deeper analysis than just sales forecasts. In particular, safety stocks that optimize the desired levels of service were among the most frequently requested feature.

Our initial specification for the "safety stocks" application includes a report that displays, for every product (or every SKU if there are multiple storage locations),

• Past sales (grabbed from a 3rd party software).
• Future sales (forecasted by Lokad).
• Stock level (grabbed from a 3rd party software).
• Stock coverage (computed), the time to reach the stock out if no reorder is made.
• Supplier (manually entered), just to be able to sort the products against their respective suppliers.
• Lead time (manually entered).
• Service factor (manually entered), the desired probably to get a stock-out.
• Reorder point (computed), the suggested amount of inventory that should trigger a reorder.
• Delta stock (computed as stock at hand minus reorder point), it tells you how much over-stock you have.

Like we did already, this application will be released as open source under SourceForge. If you think we should include more features, do not hesitate to contact us or to directly submit a feature request.

Accurate forecasts are critical because each extra-percent of forecast error comes with a steep price, literally. Indeed, when the costs associated to forecast errors are usually supra-linear, or put more simply, the costs associated to forecast errors increase much faster than the error itself.

As a simple example, a greater forecast error increases the need for safety stocks and thus working capital requirements. But if the working capital goes too high, bank interests start to rise, leading to even more expensive safety stocks.

But there are also more subtle negative consequences: past forecast errors may lower future accuracy. Indeed, historical demand itself is rarely known, instead, we usually rely on the historical sales data as an efficient approximation of the demand. Yet, this approximation is not perfect. For example, a stock-out prevents any sale to be made for a particular product. Yet, in case of a stock-out, zero sale does not equate zero demand.

For statistical forecasting algorithms, that relies on time-series analysis, it can be quite hard, using the sole sales data, to distinguish a zero sale caused by a stock-out from a zero demand. As a result, a lot of stock-outs (as they lead to lower sales) can be statistically interpreted as a lower demand; which, eventually, generates even more stock-outs.

Increasing your forecast accuracy now is one of the key to increase the forecast accuracy tomorrow. Accurate forecasting is not the destination but the journey.