Python-bloggers

On Day 21, we wrung our hands with frustration over how to proceed. The results of our circular block sampling suggested we shouldn’t expect a whole lot of outperformance in our 12-by-12 model out-of-sample. To deal with this our choices were, back ...

BigQuery ML has revolutionised how data scientists build machine learning models in data warehouses. BQML linear regression helps create accurate predictions right where your data lives. You can use SQL to build models that are just as reliable as traditional methods but without the usual complexity. Linear regression is one ...

On Day 20 we completed our analysis of the 12-by-12 strategy using circular block sampling on the 3 and 7 blocks. We found the strategy did not outperform buy-and-hold on average and its frequency of outperformance was modest – in the 28-31% range –...

GLMNet in Python: Generalized Linear Model, within the Techtonique ecosystem (nnetsauce, mlsauce)

Introduction JavaScript stands out as a clear winner in popular markup and scripting languages. If you don’t believe us, here’s the proof, Stack Overflow’s Annual Developer Survey tells us: Over 63% of 90,000+ respondents prefer working with JavaScript. Why is it so? Besides a readable (and HTML-friendly) syntax, flexibility, ...

Gaming’s death scenarios have developed well beyond the simple “Game Over” screen we saw in earlier times. “Death by AI prompts” has transformed how players experience virtual mortality. This new approach creates sophisticated and customized end-game scenarios by combining artificial intelligence with creative storytelling. Players now see unique death ...

AI-powered code generation raises an intriguing question about the differences between artificial neural attention and human thought processes in writing code. Developers take years to become skilled at programming through hands-on experience and intuition. Neural models, however, tackle code generation through mathematical attention mechanisms and pattern recognition. The comparison between ...

On Day 19, we introduced circular block sampling and used it to test the likelihood the 200-day SMA strategy would outperform buy-and-hold over a five year period. We found that the 200-day outperformed buy-and-hold a little over 25% of the time acr...

On Day 18 we started to discuss simulating returns to quantify the probability of success for a strategy out-of-sample. The reason for this was we were unsure whether or how much to merit the 12-by-12’s performance relative to the 200-Day SMA. We di...

On Day 17 , we compared the 12-by-12 and 200-day SMA strategies in terms of magnitude and duration of drawdowns, finding in favor of the 200-day. We also noted that most of the contributors to the differences in performance were due to two periods a...