The Bangalore reclassification happened in 2011 when it split into multiple administrative zones, and our data switches from city-level to aggregated-zones starting that year. The aggregates are supposed to be equivalent, but the actual numbers jumped 8%, which might reflect either a genuine change in what's being measured or residual data-quality differences. Should we add a note about this reclassification and its potential impact on trend analysis?
Adding this to the review list.
Can you split Q3 out?
Balin Mayene Is the forecasting model trained on the historical period that includes this anomaly, or did we exclude it as an outlier — and if so, doesn't that make the forecast artificially conservative?
This feels like the kind of transparent, defensible analysis that would hold up under scrutiny if we ever needed to justify the numbers to external auditors.
Is the 2019 gap a currency effect, or is the series genuinely missing?
Should this be a log scale?
Minor: throughput is mislabelled in the tooltip.
FYI.
Why does Kenya dip in 2012?