The translation industry has been incredibly slow to adopt a data-driven operations version. As other businesses have achieved so and seen efficiency skyrocket, the translation services torontoe was hindered by a continuing reliance on old-school job administration. In Gengo, we believe change is overdue.
In 2016, our community of over 21,000 translators interpreted 218 million units (characters or words ) on our platform, an equivalent of over 597,000 units per day. 95% of customer orders have been started within two hours of order placement and 99% over 5 hours. Our secret is placing translation information in the heart of Gengo’s operations. Translator behaviour information and customer ordering patterns have been analyzed to identify gaps where translator coverage is weak and can be improved. Doing this lets us match the spikes and troughs of our clients’ demand with flexible and agile translation distribution, resulting in fast turnaround times and large output.
A case in point: The 2016 vacations
Every year, the last two weeks of December see activity among the translator community shed as many take time off. The impact to Gengo varies from language to language since distinct countries celebrate the holidays to varying degrees. Christmas is an important holiday in the US while it’s scarcely celebrated in Japan. Not a week later, it is Japan who is in full holiday mode for New Year’s day and the majority of people take several days off after Jan 1. To complicate matters, the essence of translation is such that translators and customers are often located in various states and therefore on conflicting schedules. This presents a exceptional supply challenge which could be solved by taking a data-driven strategy.
We see from historic data for 2015 and past years that vacation customer purchasing patterns are generally predictable on a macro level. Order volume tends to fall towards the Christmas vacation and increases back up at the work days after the holiday to approximately 50% of normal quantity. Orders then fall back down towards New Year’s day before eventually ramping back up fast to normal levels from the first workday of the Japanese calendar (most customers included in this investigation are located in Japan). We also see greater volatility at translator availability around Christmas time, leading to more customers needing translation compared to translators willing to supply it. This means clients receive their translations slower than usual.
Forecasting order quantity
To get ready for the approaching 2016 holiday period, we applied these learnings by predicting order volume per day, as shown in Chart 1 below. We took a conservative approach, predicting quantity on the side for redundancy. Note that predictions or actuals said here didn’t incorporate a number of customers since their projects were managed separately.