DBTB INT Manish Singh

on YouTube ↗03m

" summary

CTO of MityLytics argues that generic benchmarks mislead and that real projects require run your own loads and export actual job traces to characterize workloads. Big data value comes from scalable processing plus visualization, not theory, and cost-performance wins by matching cluster size and storage choices to measured throughput and latency. The advice is practical: gather real numbers, compare actual runtimes and costs, and tune configuration rather than trusting published benchmarks.

AI-written summary · about

" related talks

• 05mApply Small Data to Big DataBaron Schwartz, Kyle Redinger · Strata Conference New York + Hadoop World 2013
• 49mdbt: A Software Engineering Approach To The Analytics WorkflowKshitij Aranke, Brandon Segal · Philly ETE 2023
• 23mData Team as an Optimisation ProblemMike Gouline · DataEngBytes 2020
• 22mDataEngBytes 2023 - BRI-T1-06 - Yanir SeroussiYanir Seroussi · DataEngBytes Brisbane 2023
• 01h 06mBest practices when accessing Big Data or any other data!Rosemary Francis · ACCU 2019
• 23mDelivering Modern Data Stacks With dbt to Operationalise AnalyticsTim Harrison, Ernesto Ongaro · Big Data LDN 2022
• 40mArchitecting for Data-Intensive WorkloadsOvidiu Hutuleac · JCON WORLD ONLINE 2023
• 01h 00mThomas in't Veld | Data Track | Compass AI & Data Summit 2025Thomas in't Veld · Compass AI & Data Summit 2025