Archives in the Cloud
Exploring machine learning to transform Archives New Zealand’s digital services for agencies
DOI:
https://doi.org/10.26686/arch.10537Keywords:
machine learning, Archives New Zealand, AppraisalAbstract
Kei ngā iwi o te ao nei, ehara taku toa te toa takitahi, engari he toa takitini. Nō reira, tēnā koutou, tēnā koutou, tēnā koutou katoa.
To the many people of the world, it is not through my strength alone but the strength of the many that we will succeed. Greetings thrice over to all.
Between February and July 2022, Archives New Zealand Te Rua Mahara o te Kāwanatanga (Archives) led a proof of concept (PoC) to see how best it could transfer and identify high value agency data, including information that is of interest to Māori. This proof of concept involved analysing hyperscale cloud capabilities and machine learning tools to see how a cloud service provider can support our need to deliver. This article summarises the process and findings of the draft report. While the PoC is only a first exploratory step, findings will be used as a base for future learnings. Any policy decisions or redesigns of our archival management systems would be a separate process.